ClawAudit verdict
tencent-docs
The skill is a documented MCP integration for Tencent Docs using an explicitly declared token; all capabilities align with the stated document management purpose.
⚠ 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.
Findings (2)
Long base64 string (100+ chars) — likely obfuscated payload
references/docengine_references.md · code · IyDmoIfpopgKCui/meaYr+S4gOautSoq5Yqg57KXKirmlofmnKzjgIIKCi0g5YiX6KGo6aG5MQotIOWI
References child_process — can spawn system processes
generate_slide.js · prose · downgraded · child_process
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.
Is this flag fair?
Thanks — recorded.