Merge fix/kvb-check-security-accept-key-collision into unify/skills-20261111
🧪 Test / 🧪 Lock + lint (push) Canceled after 0s
🧪 Test / 🧪 Lock + lint (push) Canceled after 0s
This commit is contained in:
commit
fd8fc08603
3 files changed
+94
-21
No files matched your search
@@ -46,10 +46,12 @@ value. Pass `<n>` as `--security` and the critical count as `--critical`
|
|||||||
`--security '~<n>'` (quoted: zsh expands a bare `~100` as a user's home) and the critical findings you found as `--critical`.
|
`--security '~<n>'` (quoted: zsh expands a bare `~100` as a user's home) and the critical findings you found as `--critical`.
|
||||||
- Exit 2: usage error.
|
- Exit 2: usage error.
|
||||||
- **Accepted false positives**: `security.py accept --repo <root> --rule
|
- **Accepted false positives**: `security.py accept --repo <root> --rule
|
||||||
<id> [--rule <id> ...] --path <path> --sha1 <sha1> --reason "<one line>"`
|
<id> [--rule <id> ...] --path <path> --sha1 <sha1> --line <n> --reason "<one line>"`
|
||||||
(from `--json`) appends a row per rule to the council root, which the
|
(from `--json`) appends a row per rule to the council root, which the
|
||||||
`kvb-org-organize` watch hook mirrors to `~/.local/state/agents-council/`.
|
`kvb-org-organize` watch hook mirrors to `~/.local/state/agents-council/`.
|
||||||
A match leaves the score as `<a> accepted` until the line changes. Accept
|
A match leaves the score as `<a> accepted` until the line or its
|
||||||
|
neighbourhood changes; `--line` is required when the same text occurs on
|
||||||
|
several lines, so one acceptance never hides an identical line. Accept
|
||||||
only after `kvb-think-criticize` judged it a false positive or by design;
|
only after `kvb-think-criticize` judged it a false positive or by design;
|
||||||
name each acceptance in the commit message.
|
name each acceptance in the commit message.
|
||||||
|
|
||||||
|
|||||||
@@ -6,9 +6,11 @@ Args:
|
|||||||
--base: git ref the change starts from.
|
--base: git ref the change starts from.
|
||||||
--json: print the figures as JSON instead of the line.
|
--json: print the figures as JSON instead of the line.
|
||||||
|
|
||||||
accept --repo <root> --rule <rule_id> [--rule ...] --path <repo path> --sha1 <40 hex> --reason <one line>:
|
accept --repo <root> --rule <rule_id> [--rule ...] --path <repo path> --sha1 <40 hex> [--line <n>] --reason <one line>:
|
||||||
record reviewed false positives of one line instead, a row per rule; --json
|
record reviewed false positives of one line instead, a row per rule; --json
|
||||||
of a scan prints rule, path and sha1 of every finding.
|
of a scan prints rule, path, line and sha1 of every finding. --line binds
|
||||||
|
the row to that line's neighbourhood and is required when the line's text
|
||||||
|
occurs more than once in the file.
|
||||||
|
|
||||||
Scan:
|
Scan:
|
||||||
The regular files `git diff <ref>` names plus untracked ones, symlinks left
|
The regular files `git diff <ref>` names plus untracked ones, symlinks left
|
||||||
@@ -20,13 +22,17 @@ Scan:
|
|||||||
|
|
||||||
Accepted:
|
Accepted:
|
||||||
One JSON row per reviewed false positive (id, rule, path, sha1 of the stripped
|
One JSON row per reviewed false positive (id, rule, path, sha1 of the stripped
|
||||||
source line, or of the whole file for a finding without a line, reason, repo,
|
source line, or of the whole file for a finding without a line, context: the
|
||||||
date), appended by accept to
|
sha1 of the stripped lines up to REACH above and below it when accept got
|
||||||
|
--line, reason, repo, date), appended by accept to
|
||||||
<council root>/security-accepted.jsonl of the kvb-org-organize watch.py, whose
|
<council root>/security-accepted.jsonl of the kvb-org-organize watch.py, whose
|
||||||
hook keeps the rows in ~/.local/state/agents-council/security-accepted.jsonl;
|
hook keeps the rows in ~/.local/state/agents-council/security-accepted.jsonl;
|
||||||
a scan reads both. A finding with that rule, path and text is accepted and
|
a scan reads both. A finding with that rule, path, text and context is
|
||||||
leaves the score; an edit of the line, or of the file, brings it back. A row
|
accepted and leaves the score; a row without context accepts it only while no
|
||||||
without rule, path and sha1 is a usage error.
|
other finding of the scan shares its rule, path and text, so one acceptance
|
||||||
|
never hides an identical line elsewhere. An edit of the line, its
|
||||||
|
neighbourhood or the file brings it back. A row without rule, path and sha1
|
||||||
|
is a usage error.
|
||||||
|
|
||||||
Output:
|
Output:
|
||||||
`🛡️ security <n> % (medusa: <k> findings, <a> accepted in <m> files: <severity> <path>:<line>, ...)`,
|
`🛡️ security <n> % (medusa: <k> findings, <a> accepted in <m> files: <severity> <path>:<line>, ...)`,
|
||||||
@@ -55,11 +61,13 @@ import shutil
|
|||||||
import subprocess
|
import subprocess
|
||||||
import sys
|
import sys
|
||||||
import tempfile
|
import tempfile
|
||||||
|
from collections import Counter
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
|
||||||
WEIGHTS = {"critical": 50, "high": 25, "medium": 10, "low": 2, "info": 0}
|
WEIGHTS = {"critical": 50, "high": 25, "medium": 10, "low": 2, "info": 0}
|
||||||
SAFE = 100
|
SAFE = 100
|
||||||
SHOWN = 5
|
SHOWN = 5
|
||||||
|
REACH = 2
|
||||||
SHA1 = re.compile(r"[0-9a-f]{40}")
|
SHA1 = re.compile(r"[0-9a-f]{40}")
|
||||||
WATCH = Path(__file__).resolve().parents[2] / "kvb-org-organize" / "scripts" / "watch.py"
|
WATCH = Path(__file__).resolve().parents[2] / "kvb-org-organize" / "scripts" / "watch.py"
|
||||||
HAND = (
|
HAND = (
|
||||||
@@ -115,17 +123,27 @@ def located(name: str, tree: Path) -> str:
|
|||||||
return name
|
return name
|
||||||
|
|
||||||
|
|
||||||
def fingerprint(tree: Path, path: str, line: int | None) -> str | None:
|
def digest(text: str) -> str:
|
||||||
|
return hashlib.sha1(text.encode()).hexdigest()
|
||||||
|
|
||||||
|
|
||||||
|
def fingerprint(tree: Path, path: str, line: int | None) -> tuple[str | None, str | None]:
|
||||||
|
"""Returns:
|
||||||
|
(sha1 of the stripped line or of the whole file without a line, sha1 of
|
||||||
|
the stripped lines up to REACH around the line or None), (None, None) for
|
||||||
|
an unreadable file or a line outside it.
|
||||||
|
"""
|
||||||
try:
|
try:
|
||||||
text = (tree / path).read_text(encoding="utf-8", errors="replace")
|
text = (tree / path).read_text(encoding="utf-8", errors="replace")
|
||||||
except OSError:
|
except OSError:
|
||||||
return None
|
return None, None
|
||||||
if line is None:
|
if line is None:
|
||||||
return hashlib.sha1(text.encode()).hexdigest()
|
return digest(text), None
|
||||||
rows = text.splitlines()
|
rows = text.splitlines()
|
||||||
if not 1 <= line <= len(rows):
|
if not 1 <= line <= len(rows):
|
||||||
return None
|
return None, None
|
||||||
return hashlib.sha1(rows[line - 1].strip().encode()).hexdigest()
|
around = rows[max(0, line - 1 - REACH):line + REACH]
|
||||||
|
return digest(rows[line - 1].strip()), digest("\n".join(row.strip() for row in around))
|
||||||
|
|
||||||
|
|
||||||
def watch():
|
def watch():
|
||||||
@@ -137,7 +155,7 @@ def watch():
|
|||||||
return loaded
|
return loaded
|
||||||
|
|
||||||
|
|
||||||
def accepted(listings: tuple[Path, ...]) -> set[tuple[str, str, str]]:
|
def accepted(listings: tuple[Path, ...]) -> set[tuple[str, str, str, str | None]]:
|
||||||
entries = set()
|
entries = set()
|
||||||
for listing in listings:
|
for listing in listings:
|
||||||
if not listing.is_file():
|
if not listing.is_file():
|
||||||
@@ -147,28 +165,48 @@ def accepted(listings: tuple[Path, ...]) -> set[tuple[str, str, str]]:
|
|||||||
continue
|
continue
|
||||||
try:
|
try:
|
||||||
row = json.loads(line)
|
row = json.loads(line)
|
||||||
entries.add((row["rule"], row["path"], row["sha1"]))
|
entries.add((row["rule"], row["path"], row["sha1"], row.get("context")))
|
||||||
except (ValueError, KeyError, TypeError):
|
except (ValueError, KeyError, TypeError, AttributeError):
|
||||||
fail(f"{listing}:{number}: want a JSON row with rule, path and sha1")
|
fail(f"{listing}:{number}: want a JSON row with rule, path and sha1")
|
||||||
return entries
|
return entries
|
||||||
|
|
||||||
|
|
||||||
|
def covered(finding: dict, reviewed: set[tuple[str, str, str, str | None]], shared: Counter) -> bool:
|
||||||
|
key = (finding["rule"], finding["path"], finding["sha1"])
|
||||||
|
return (*key, finding["context"]) in reviewed or (shared[key] == 1 and (*key, None) in reviewed)
|
||||||
|
|
||||||
|
|
||||||
def accept(argv: list[str]) -> int:
|
def accept(argv: list[str]) -> int:
|
||||||
parser = argparse.ArgumentParser(prog="security.py accept", description="Record a reviewed false positive.")
|
parser = argparse.ArgumentParser(prog="security.py accept", description="Record a reviewed false positive.")
|
||||||
for flag in ("--repo", "--path", "--sha1", "--reason"):
|
for flag in ("--repo", "--path", "--sha1", "--reason"):
|
||||||
parser.add_argument(flag, required=True)
|
parser.add_argument(flag, required=True)
|
||||||
parser.add_argument("--rule", action="append", required=True)
|
parser.add_argument("--rule", action="append", required=True)
|
||||||
|
parser.add_argument("--line", type=int)
|
||||||
args = parser.parse_args(argv)
|
args = parser.parse_args(argv)
|
||||||
if not SHA1.fullmatch(args.sha1):
|
if not SHA1.fullmatch(args.sha1):
|
||||||
parser.error("--sha1 must be 40 lowercase hex digits")
|
parser.error("--sha1 must be 40 lowercase hex digits")
|
||||||
if not args.reason.strip() or "\n" in args.reason:
|
if not args.reason.strip() or "\n" in args.reason:
|
||||||
parser.error("--reason must be one non-empty line")
|
parser.error("--reason must be one non-empty line")
|
||||||
root = git(Path(args.repo), "rev-parse", "--show-toplevel").strip()
|
root = git(Path(args.repo), "rev-parse", "--show-toplevel").strip()
|
||||||
|
context = None
|
||||||
|
if args.line is not None:
|
||||||
|
sha1, context = fingerprint(Path(root), args.path, args.line)
|
||||||
|
if sha1 != args.sha1:
|
||||||
|
parser.error(f"--sha1 is not the sha1 of line {args.line} of {args.path}")
|
||||||
|
else:
|
||||||
|
try:
|
||||||
|
rows = (Path(root) / args.path).read_text(encoding="utf-8", errors="replace").splitlines()
|
||||||
|
except OSError:
|
||||||
|
rows = []
|
||||||
|
twins = sum(digest(row.strip()) == args.sha1 for row in rows)
|
||||||
|
if twins > 1:
|
||||||
|
parser.error(f"the line occurs {twins} times in {args.path}; name the reviewed one with --line")
|
||||||
date = datetime.datetime.now(datetime.UTC).isoformat(timespec="seconds")
|
date = datetime.datetime.now(datetime.UTC).isoformat(timespec="seconds")
|
||||||
rows = [
|
rows = [
|
||||||
{
|
{
|
||||||
"id": hashlib.sha1(f"{rule}\t{args.path}\t{args.sha1}".encode()).hexdigest(), "rule": rule,
|
"id": digest("\t".join([rule, args.path, args.sha1, *([context] if context else [])])), "rule": rule,
|
||||||
"path": args.path, "sha1": args.sha1, "reason": args.reason, "repo": root, "date": date,
|
"path": args.path, "sha1": args.sha1, **({"context": context} if context else {}),
|
||||||
|
"reason": args.reason, "repo": root, "date": date,
|
||||||
}
|
}
|
||||||
for rule in args.rule
|
for rule in args.rule
|
||||||
]
|
]
|
||||||
@@ -199,12 +237,14 @@ def findings(reports: Path, tree: Path) -> list[dict]:
|
|||||||
raise Unreadable(f"{files[-1].name}: a finding without a known severity")
|
raise Unreadable(f"{files[-1].name}: a finding without a known severity")
|
||||||
line = entry.get("line") if isinstance(entry.get("line"), int) else None
|
line = entry.get("line") if isinstance(entry.get("line"), int) else None
|
||||||
path = located(str(entry.get("file") or "?"), tree)
|
path = located(str(entry.get("file") or "?"), tree)
|
||||||
|
sha1, context = fingerprint(tree, path, line)
|
||||||
found.append({
|
found.append({
|
||||||
"severity": severity,
|
"severity": severity,
|
||||||
"rule": entry.get("rule_id") if isinstance(entry.get("rule_id"), str) else None,
|
"rule": entry.get("rule_id") if isinstance(entry.get("rule_id"), str) else None,
|
||||||
"path": path,
|
"path": path,
|
||||||
"line": line,
|
"line": line,
|
||||||
"sha1": fingerprint(tree, path, line),
|
"sha1": sha1,
|
||||||
|
"context": context,
|
||||||
})
|
})
|
||||||
rank = list(WEIGHTS)
|
rank = list(WEIGHTS)
|
||||||
return sorted(found, key=lambda f: (rank.index(f["severity"]), f["path"], f["line"] or 0))
|
return sorted(found, key=lambda f: (rank.index(f["severity"]), f["path"], f["line"] or 0))
|
||||||
@@ -266,7 +306,8 @@ def main() -> int:
|
|||||||
print(f"🛡️ security – ({problem}: {HAND})")
|
print(f"🛡️ security – ({problem}: {HAND})")
|
||||||
return 4
|
return 4
|
||||||
|
|
||||||
passed = [f for f in every if (f["rule"], f["path"], f["sha1"]) in reviewed]
|
shared = Counter((f["rule"], f["path"], f["sha1"]) for f in every)
|
||||||
|
passed = [f for f in every if covered(f, reviewed, shared)]
|
||||||
found = [f for f in every if f not in passed]
|
found = [f for f in every if f not in passed]
|
||||||
counts = {severity: sum(f["severity"] == severity for f in found) for severity in WEIGHTS}
|
counts = {severity: sum(f["severity"] == severity for f in found) for severity in WEIGHTS}
|
||||||
value = max(0, SAFE - sum(WEIGHTS[s] * n for s, n in counts.items()))
|
value = max(0, SAFE - sum(WEIGHTS[s] * n for s, n in counts.items()))
|
||||||
|
|||||||
@@ -108,6 +108,7 @@ class TestSecurity(unittest.TestCase):
|
|||||||
{
|
{
|
||||||
"severity": "high", "rule": "FAKE-HIGH", "path": "app.py", "line": 2,
|
"severity": "high", "rule": "FAKE-HIGH", "path": "app.py", "line": 2,
|
||||||
"sha1": hashlib.sha1(f"token = '{PLACEHOLDER}' # MARK-HIGH".encode()).hexdigest(),
|
"sha1": hashlib.sha1(f"token = '{PLACEHOLDER}' # MARK-HIGH".encode()).hexdigest(),
|
||||||
|
"context": hashlib.sha1(f"print(1)\ntoken = '{PLACEHOLDER}' # MARK-HIGH".encode()).hexdigest(),
|
||||||
},
|
},
|
||||||
)
|
)
|
||||||
self.assertEqual(found["accepted"], [])
|
self.assertEqual(found["accepted"], [])
|
||||||
@@ -148,6 +149,35 @@ class TestSecurity(unittest.TestCase):
|
|||||||
("🛡️ security 50 % (medusa: 1 finding in 1 file: critical app.py:2)\n", 1),
|
("🛡️ security 50 % (medusa: 1 finding in 1 file: critical app.py:2)\n", 1),
|
||||||
)
|
)
|
||||||
|
|
||||||
|
def test_one_acceptance_never_hides_an_identical_line_elsewhere(self):
|
||||||
|
twin = "x = fetch(url) # MARK-HIGH"
|
||||||
|
self.write("app.py", f"print(1)\n{twin}\ny = 2\n{twin}\n")
|
||||||
|
sha1 = hashlib.sha1(twin.encode()).hexdigest()
|
||||||
|
both = ("🛡️ security 50 % (medusa: 2 findings in 1 file: high app.py:2, high app.py:4)\n", 3)
|
||||||
|
listing = self.base / "council" / "security-accepted.jsonl"
|
||||||
|
listing.parent.mkdir(parents=True)
|
||||||
|
listing.write_text(json.dumps({"rule": "FAKE-HIGH", "path": "app.py", "sha1": sha1}) + "\n", encoding="utf-8")
|
||||||
|
result = self.scan(env=self.env)
|
||||||
|
self.assertEqual((result.stdout, result.returncode), both)
|
||||||
|
listing.unlink()
|
||||||
|
refused = self.accept("--rule", "FAKE-HIGH", "--path", "app.py", "--sha1", sha1, "--reason", "fixture")
|
||||||
|
self.assertEqual(refused.returncode, 2)
|
||||||
|
self.assertIn("the line occurs 2 times in app.py; name the reviewed one with --line", refused.stderr)
|
||||||
|
self.assertFalse(listing.exists())
|
||||||
|
wrong = self.accept("--rule", "FAKE-HIGH", "--path", "app.py", "--sha1", sha1, "--line", "3", "--reason", "fixture")
|
||||||
|
self.assertEqual(wrong.returncode, 2)
|
||||||
|
self.assertIn("--sha1 is not the sha1 of line 3 of app.py", wrong.stderr)
|
||||||
|
named = self.accept("--rule", "FAKE-HIGH", "--path", "app.py", "--sha1", sha1, "--line", "4", "--reason", "fixture")
|
||||||
|
self.assertEqual(named.returncode, 0, named.stderr)
|
||||||
|
result = self.scan(env=self.env)
|
||||||
|
self.assertEqual(
|
||||||
|
(result.stdout, result.returncode),
|
||||||
|
("🛡️ security 75 % (medusa: 1 finding, 1 accepted in 1 file: high app.py:2)\n", 3),
|
||||||
|
)
|
||||||
|
self.write("app.py", f"print(1)\n{twin}\ny = 3\n{twin}\n")
|
||||||
|
result = self.scan(env=self.env)
|
||||||
|
self.assertEqual((result.stdout, result.returncode), both)
|
||||||
|
|
||||||
def test_kept_rows_count_and_broken_rows_stop(self):
|
def test_kept_rows_count_and_broken_rows_stop(self):
|
||||||
line = "y = other() # MARK-HIGH"
|
line = "y = other() # MARK-HIGH"
|
||||||
self.write("app.py", f"{line}\n")
|
self.write("app.py", f"{line}\n")
|
||||||
|
|||||||
Reference in new issue
Block a user