ClawAudit verdict

gitlab-weekly-report

gitlab-team-report

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

GitLab weekly report generator that reads config/config.json with user-provided credentials to query GitLab MRs and generate local Markdown/HTML reports with optional Feishu publishing.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

30
security
50
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match high

<script> tag in markdown — potential code injection

scripts/generate-report.py · prose · downgraded · <script

Pattern match high

Possible hardcoded credential

scripts/upload-to-feishu.sh · prose · downgraded · SECRET="${FEISHU_APP_SECRET:-$(jq -r

Pattern match medium

pip3 install — installs Python packages at runtime

SKILL.md · code · pip3 install

Pattern match medium

subprocess execution — runs system commands from Python

scripts/generate-report.py · prose · downgraded · subprocess.run(

Pattern match low

Python urllib.request — network access

scripts/generate-report.py · prose · downgraded · urllib.request

Pattern match low

Accesses sensitive environment variables

scripts/upload-to-feishu.js · prose · downgraded · process.env.FEISHU_USER_ACCESS_TOKEN

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

package_install

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API