autonomic-bot
cf26ef863a
Anonymous GitHub API is 60 req/hr — a full weekly sweep across ~20 recipes exhausts it and the scan then reports sources as failed (visible, but degraded coverage). A token lifts it to 5000/hr. _github_token(): GITHUB_TOKEN env wins, else GITHUB_TOKEN_FILE (default /srv/cc-ci/.github-token, 0600, gitignored). Reading PUBLIC advisories needs NO scopes — a classic PAT with nothing ticked, or fine-grained limited to 'Public repositories: read'. The tool only ever GETs advisories; do not grant write scopes. A missing token is not an error: the scan runs anonymously and surfaces failures. Also gitignores .github-token and .hcloud-token.
314 lines
14 KiB
Python
Executable File
314 lines
14 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Deterministic per-recipe CVE/advisory scan — an ADDITIVE pre-step for /recipe-upgrade.
|
|
|
|
WHY THIS EXISTS (2026-08-10): gitea 1.27.1 fixed two CVSS-9.8 RCEs (CVE-2026-60004,
|
|
CVE-2026-59774). Our weekly report showed gitea's CVE count as "1", then "none". The upgrade
|
|
subagent had scanned the GitHub *release notes*, which mention neither; the two CVEs were announced
|
|
only in the vendor's blog security section. The report generator then derived security content from
|
|
those notes plus model knowledge — and the model's training predates the CVEs. Nothing in the
|
|
pipeline ever queried an advisory source, so a critical CVE that is newer than the model and absent
|
|
from the changelog was invisible by construction.
|
|
|
|
WHAT IT DOES NOT DO: it does not replace or alter any existing security analysis. It is a strictly
|
|
ADDITIONAL evidence source whose findings are unioned into the CVE count.
|
|
|
|
SOURCES (measured against the gitea case before being chosen):
|
|
1. GitHub Security Advisories API — repos/<owner>/<repo>/security-advisories. PRIMARY: carries
|
|
CVE id, GHSA id, severity AND vulnerable/patched version ranges, so "fixed by THIS upgrade" is
|
|
computable rather than guessed. Found both gitea CVEs. Derived from the source-repo URLs the
|
|
per-recipe registry already records — no new per-recipe config needed.
|
|
2. Vendor release/security pages — every URL in cc-ci-plan/upstream/<recipe>.md, fetched and
|
|
regex-scanned for CVE ids. This is what would have caught gitea: the vendor blog names both,
|
|
while the GitHub releases page names neither. Add vendor security/announcement URLs to the
|
|
registry to widen this.
|
|
3. OSV.dev — supplementary, best-effort, only when the recipe declares an ecosystem/package
|
|
mapping below. NOTE: for gitea, OSV returned only Go *dependency* advisories and 404'd on both
|
|
application CVEs; NVD's API had them neither by CPE, CVE id, nor keyword. Advisory databases
|
|
lag the vendor — which is exactly why (1) and (2) lead.
|
|
|
|
Every source reports its own status, so "checked, none found" is never confused with "not checked".
|
|
|
|
Usage:
|
|
advisory-scan.py <recipe> [--from <version>] [--to <version>] [--json] [--registry DIR]
|
|
|
|
--from/--to are the app versions being upgraded between (e.g. 1.26.2 -> 1.27.1). When given, each
|
|
advisory is classified fixed-by-this-upgrade / still-open / older. Without them everything known
|
|
is listed unclassified. Exits 0 even when sources fail (informational; failures are reported).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import gzip
|
|
import json
|
|
import os
|
|
import re
|
|
import sys
|
|
import urllib.error
|
|
import urllib.request
|
|
|
|
REGISTRY_DIR = os.environ.get("CCCI_UPSTREAM_REGISTRY", "/srv/cc-ci/cc-ci-plan/upstream")
|
|
UA = "cc-ci-advisory-scan (+https://git.autonomic.zone/recipe-maintainers/cc-ci)"
|
|
TIMEOUT = int(os.environ.get("ADVISORY_SCAN_TIMEOUT", "45"))
|
|
CVE_RE = re.compile(r"CVE-\d{4}-\d{4,7}")
|
|
|
|
# Optional OSV mappings: recipe -> (ecosystem, package). Supplementary only (see module docstring).
|
|
OSV_PACKAGES: dict[str, tuple[str, str]] = {
|
|
"gitea": ("Go", "code.gitea.io/gitea"),
|
|
"n8n": ("npm", "n8n"),
|
|
}
|
|
|
|
|
|
def _github_token() -> str | None:
|
|
"""Read-only GitHub token, for the API rate limit ONLY (60/hr anonymous → 5000/hr with a token).
|
|
|
|
Env `GITHUB_TOKEN` wins; otherwise the file at `GITHUB_TOKEN_FILE` (default
|
|
/srv/cc-ci/.github-token, chmod 600, never in git). Reading PUBLIC security advisories needs NO
|
|
scopes at all — create a classic PAT with every box unticked, or a fine-grained token limited to
|
|
"Public repositories: read". Do NOT grant repo/write scopes: this tool only ever GETs advisories.
|
|
A missing token is not an error — the scan simply runs anonymously and will report sources as
|
|
failed once the 60/hr limit bites, which is visible rather than silent.
|
|
"""
|
|
tok = os.environ.get("GITHUB_TOKEN")
|
|
if tok:
|
|
return tok.strip()
|
|
path = os.environ.get("GITHUB_TOKEN_FILE", "/srv/cc-ci/.github-token")
|
|
try:
|
|
with open(path) as f:
|
|
return f.read().strip() or None
|
|
except OSError:
|
|
return None
|
|
|
|
|
|
def _fetch(url: str, headers: dict | None = None) -> str:
|
|
h = {"User-Agent": UA, "Accept-Encoding": "gzip"}
|
|
h.update(headers or {})
|
|
with urllib.request.urlopen(urllib.request.Request(url, headers=h), timeout=TIMEOUT) as r:
|
|
raw = r.read()
|
|
if r.headers.get("Content-Encoding") == "gzip":
|
|
raw = gzip.decompress(raw)
|
|
return raw.decode(errors="replace")
|
|
|
|
|
|
def _vkey(v: str | None) -> tuple:
|
|
"""Loose version ordering key: leading integers of each dot-part ('1.27.1-rootless' -> (1,27,1))."""
|
|
if not v:
|
|
return ()
|
|
v = v.strip().lstrip("vV").split("+")[0]
|
|
out = []
|
|
for part in re.split(r"[.\-_]", v):
|
|
m = re.match(r"^\d+", part)
|
|
if m:
|
|
out.append(int(m.group()))
|
|
elif out:
|
|
break
|
|
return tuple(out)
|
|
|
|
|
|
def registry_urls(recipe: str, registry_dir: str) -> tuple[list[str], str | None]:
|
|
path = os.path.join(registry_dir, f"{recipe}.md")
|
|
try:
|
|
with open(path) as f:
|
|
text = f.read()
|
|
except OSError:
|
|
return [], None
|
|
urls = []
|
|
for u in re.findall(r"https?://[^\s)|\]]+", text):
|
|
u = u.rstrip(".,;")
|
|
if u not in urls:
|
|
urls.append(u)
|
|
return urls, path
|
|
|
|
|
|
def github_advisories(urls: list[str]) -> list[dict]:
|
|
"""Query GitHub Security Advisories for every github.com/<owner>/<repo> in the registry."""
|
|
seen, results = set(), []
|
|
for u in urls:
|
|
m = re.match(r"https?://github\.com/([^/]+)/([^/#?]+)", u)
|
|
if not m:
|
|
continue
|
|
owner, repo = m.group(1), m.group(2).removesuffix(".git")
|
|
if (owner, repo) in seen:
|
|
continue
|
|
seen.add((owner, repo))
|
|
api = f"https://api.github.com/repos/{owner}/{repo}/security-advisories?per_page=100"
|
|
hdrs = {"Accept": "application/vnd.github+json"}
|
|
tok = _github_token()
|
|
if tok:
|
|
hdrs["Authorization"] = f"Bearer {tok}"
|
|
entry = {"source": f"github-advisories:{owner}/{repo}", "status": "ok", "advisories": []}
|
|
try:
|
|
for a in json.loads(_fetch(api, hdrs)):
|
|
vulns = a.get("vulnerabilities") or []
|
|
entry["advisories"].append(
|
|
{
|
|
"cve": a.get("cve_id"),
|
|
"ghsa": a.get("ghsa_id"),
|
|
"severity": a.get("severity"),
|
|
"summary": (a.get("summary") or "")[:200],
|
|
"vulnerable_range": vulns[0].get("vulnerable_version_range") if vulns else None,
|
|
"patched": vulns[0].get("patched_versions") if vulns else None,
|
|
"url": a.get("html_url"),
|
|
}
|
|
)
|
|
except Exception as e: # noqa: BLE001 — a dead source must be REPORTED, never silent
|
|
entry["status"] = f"error: {type(e).__name__}: {e}"
|
|
results.append(entry)
|
|
return results
|
|
|
|
|
|
def vendor_pages(urls: list[str]) -> list[dict]:
|
|
"""Fetch each registry URL and regex out CVE ids, with a little surrounding context."""
|
|
out = []
|
|
for u in urls:
|
|
if u.startswith("https://api.github.com"):
|
|
continue
|
|
entry = {"source": u, "status": "ok", "cves": [], "context": {}}
|
|
try:
|
|
text = _fetch(u)
|
|
plain = re.sub(r"<[^>]+>", " ", text)
|
|
for cve in sorted(set(CVE_RE.findall(plain))):
|
|
entry["cves"].append(cve)
|
|
i = plain.find(cve)
|
|
entry["context"][cve] = re.sub(r"\s+", " ", plain[max(0, i - 160) : i + 200]).strip()
|
|
except Exception as e: # noqa: BLE001
|
|
entry["status"] = f"error: {type(e).__name__}: {e}"
|
|
out.append(entry)
|
|
return out
|
|
|
|
|
|
def osv(recipe: str, version: str | None) -> dict | None:
|
|
pkg = OSV_PACKAGES.get(recipe)
|
|
if not pkg or not version:
|
|
return None
|
|
eco, name = pkg
|
|
entry = {"source": f"osv:{eco}/{name}@{version}", "status": "ok", "cves": []}
|
|
try:
|
|
body = json.dumps({"package": {"name": name, "ecosystem": eco}, "version": version}).encode()
|
|
req = urllib.request.Request(
|
|
"https://api.osv.dev/v1/query", data=body,
|
|
headers={"Content-Type": "application/json", "User-Agent": UA}, method="POST",
|
|
)
|
|
with urllib.request.urlopen(req, timeout=TIMEOUT) as r:
|
|
data = json.load(r)
|
|
ids = set()
|
|
for v in data.get("vulns", []):
|
|
for a in [v.get("id")] + (v.get("aliases") or []):
|
|
if a and a.startswith("CVE"):
|
|
ids.add(a)
|
|
entry["cves"] = sorted(ids)
|
|
except Exception as e: # noqa: BLE001
|
|
entry["status"] = f"error: {type(e).__name__}: {e}"
|
|
return entry
|
|
|
|
|
|
def scan(recipe: str, v_from: str | None, v_to: str | None, registry_dir: str) -> dict:
|
|
urls, reg_path = registry_urls(recipe, registry_dir)
|
|
report: dict = {
|
|
"recipe": recipe,
|
|
"from": v_from,
|
|
"to": v_to,
|
|
"registry": reg_path,
|
|
"registry_urls": len(urls),
|
|
"sources": [],
|
|
"cves": {},
|
|
}
|
|
if reg_path is None:
|
|
report["sources"].append(
|
|
{"source": f"registry:{recipe}.md", "status": "error: registry file not found"}
|
|
)
|
|
|
|
def record(cve: str, src: str, **extra):
|
|
e = report["cves"].setdefault(cve, {"sources": [], "severity": None, "ghsa": None,
|
|
"vulnerable_range": None, "patched": None, "context": None})
|
|
if src not in e["sources"]:
|
|
e["sources"].append(src)
|
|
for k, v in extra.items():
|
|
if v and not e.get(k):
|
|
e[k] = v
|
|
|
|
for entry in github_advisories(urls):
|
|
report["sources"].append({"source": entry["source"], "status": entry["status"],
|
|
"found": len(entry.get("advisories", []))})
|
|
for a in entry.get("advisories", []):
|
|
if a.get("cve"):
|
|
record(a["cve"], entry["source"], severity=a.get("severity"), ghsa=a.get("ghsa"),
|
|
vulnerable_range=a.get("vulnerable_range"), patched=a.get("patched"),
|
|
context=a.get("summary"))
|
|
|
|
for entry in vendor_pages(urls):
|
|
report["sources"].append({"source": entry["source"], "status": entry["status"],
|
|
"found": len(entry.get("cves", []))})
|
|
for cve in entry.get("cves", []):
|
|
record(cve, entry["source"], context=entry["context"].get(cve))
|
|
|
|
for version in filter(None, (v_from, v_to)):
|
|
o = osv(recipe, version)
|
|
if o:
|
|
report["sources"].append({"source": o["source"], "status": o["status"],
|
|
"found": len(o.get("cves", []))})
|
|
for cve in o.get("cves", []):
|
|
record(cve, o["source"])
|
|
|
|
# Classify against the upgrade window when we know it: an advisory is "fixed by this upgrade"
|
|
# when its patched version is newer than `from` and no newer than `to`.
|
|
kf, kt = _vkey(v_from), _vkey(v_to)
|
|
fixed, unknown = [], []
|
|
for cve, e in report["cves"].items():
|
|
kp = _vkey((e.get("patched") or "").split(",")[0].strip() or None)
|
|
if kf and kt and kp and kf < kp <= kt:
|
|
e["classification"] = "fixed-by-this-upgrade"
|
|
fixed.append(cve)
|
|
else:
|
|
e["classification"] = "unclassified" if not (kf and kt and kp) else "outside-window"
|
|
if e["classification"] == "unclassified":
|
|
unknown.append(cve)
|
|
report["fixed_by_this_upgrade"] = sorted(fixed)
|
|
report["unclassified"] = sorted(unknown)
|
|
report["cve_count_fixed"] = len(fixed)
|
|
report["cve_count_total_seen"] = len(report["cves"])
|
|
report["sources_failed"] = [s["source"] for s in report["sources"] if s["status"] != "ok"]
|
|
return report
|
|
|
|
|
|
def markdown(rep: dict) -> str:
|
|
"""Human/agent-readable block for pasting into the per-recipe upgrade log."""
|
|
L = [f"### Advisory scan (deterministic pre-step) — {rep['recipe']} "
|
|
f"{rep.get('from') or '?'} → {rep.get('to') or '?'}"]
|
|
if rep["fixed_by_this_upgrade"]:
|
|
L.append(f"\n**CVEs fixed by this upgrade: {rep['cve_count_fixed']}**\n")
|
|
L.append("| CVE | severity | fixed in | advisory | source |")
|
|
L.append("|---|---|---|---|---|")
|
|
for cve in rep["fixed_by_this_upgrade"]:
|
|
e = rep["cves"][cve]
|
|
L.append(f"| {cve} | {e.get('severity') or '?'} | {e.get('patched') or '?'} | "
|
|
f"{e.get('ghsa') or '-'} | {e['sources'][0]} |")
|
|
else:
|
|
L.append("\n**CVEs fixed by this upgrade: 0 identified by the deterministic scan.**")
|
|
if rep["unclassified"]:
|
|
L.append(f"\nSeen but not version-classified ({len(rep['unclassified'])}): "
|
|
+ ", ".join(rep["unclassified"][:12]))
|
|
if rep["sources_failed"]:
|
|
L.append(f"\n⚠ sources that FAILED (treat counts as incomplete): {', '.join(rep['sources_failed'])}")
|
|
L.append(f"\n_Sources checked: {len(rep['sources'])} "
|
|
f"({rep['registry_urls']} registry URLs + advisory APIs). This scan is ADDITIVE — it does "
|
|
f"not replace the release-note reading in the upgrade step._")
|
|
return "\n".join(L)
|
|
|
|
|
|
def main() -> int:
|
|
ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
|
|
ap.add_argument("recipe")
|
|
ap.add_argument("--from", dest="v_from", default=None)
|
|
ap.add_argument("--to", dest="v_to", default=None)
|
|
ap.add_argument("--json", action="store_true", help="emit raw JSON instead of markdown")
|
|
ap.add_argument("--registry", default=REGISTRY_DIR)
|
|
a = ap.parse_args()
|
|
rep = scan(a.recipe, a.v_from, a.v_to, a.registry)
|
|
print(json.dumps(rep, indent=2) if a.json else markdown(rep))
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|