Caveat verdict
qclaw-watchdog
This watchdog skill monitors and auto-restarts a local QClaw process and sends alerts via Feishu; file_write is for logs, package_install is for brew/gh, and all operations are local process management consistent with stated purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
file_read+write
package_install
Findings (5)
Possible hardcoded credential
SKILL.md · code · SECRET="your-secret
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://127.0.0.1
Opens WebSocket connection
SKILL.md · code · WebSocket
References child_process — can spawn system processes
watchdog.js · prose · downgraded · child_process
Accesses sensitive environment variables
watchdog.js · prose · downgraded · process.env.FEISHU_APP_SECRET
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
file_writepackage_install Is this flag fair?
Thanks — recorded.