ClawAudit verdict

weibo-manager

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

Implements a human-approval gated publish workflow for Weibo via Puppeteer with explicit anti-prompt-injection safeguards; no autonomous publishing or exfiltration behavior present.

⚠ 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.

75
security
80
transparency
80
maintenance

Findings (4)

Pattern match medium

References child_process — can spawn system processes

src/approve_post.js · prose · downgraded · child_process

Pattern match medium

setuid — privilege escalation mechanism

src/delete_latest.js · prose · downgraded · setuid

Pattern match low

Popular HTTP library — network access

package.json · prose · downgraded · axios

Pattern match low

Accesses sensitive environment variables

src/weibo_client.js · prose · downgraded · process.env.WEIBO_API_KEY

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?

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