ClawAudit verdict
zsxq-post-fetch
Enhanced knowledge community fetcher using the official zsxq-cli for auth; explicitly instructs not to read or display Keychain tokens and not to bypass permissions or forge credentials.
⚠ 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 (4)
Possible hardcoded credential
SKILL.md · code · TOKEN="your_zsxq_access_token
Accesses system credential store
SKILL.md · frontmatter · Keychain
References child_process — can spawn system processes
fetch_topics.js · prose · downgraded · child_process
Node http/https module — low-level network access
fetch_topics.js · prose · downgraded · require('https')
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 2 system binaries.
Is this flag fair?
Thanks — recorded.