ClawAudit verdict
tsmf-wechat-oa
Guides an AI to generate WeChat public account articles with user-selected themes and push drafts; the skill is primarily instructional with no credential exfiltration or suspicious behavior.
⚠ 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.
Permission integrity
credential_access
package_install
Findings (8)
Possible hardcoded credential
SKILL.md · code · api_key="your_key
Pipe to python — executes piped content as Python code
references/SKILL_OVERVIEW.md · prose · downgraded · | Python
<script> tag in markdown — potential code injection
scripts/generate_covers.py · prose · downgraded · <script
References agent configuration files
references/README.md · code · CLAUDE.md
subprocess execution — runs system commands from Python
scripts/cron_detector.py · prose · downgraded · subprocess.run(
Python shutil file operation — copies/moves/deletes files
cleanup.py · prose · downgraded · shutil.rmtree(
Python urllib.request — network access
references/SKILL_OVERVIEW.md · prose · downgraded · urllib.request
Python os.getenv — reads environment variable
scripts/ai_writer.py · prose · downgraded · os.getenv(
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.
credential_accesspackage_install Is this flag fair?
Thanks — recorded.