ClawAudit verdict

jiaozhen-factcheck

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

Tencent fact-checking skill that uses a local CLI wrapper to call the declared Tencent News API; credential access is scoped to the service's own API key and the skill explicitly prohibits auto-opening browsers or leaking keys.

⚠ 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.

security

transparency

maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (3)

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

references/installation-guide.md · code · curl -fsSL https://mat1.gtimg.com/qqcdn/qqnews/cli/hub/tencent-news/setup.sh | s

Pattern match critical

Pipe to sh — executes piped content as shell commands

references/installation-guide.md · code · | sh

Pattern match medium

Accesses shell history/config

references/installation-guide.md · prose · downgraded · ~/.zshrc

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/E). 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_access

Is this flag fair?

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