ClawAudit verdict
a2a-shib-payments
The skill installs dependencies using npm, which could potentially be used for malicious purposes, but the overall intent appears to be legitimate.
⚠ 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.
Permission integrity
network_out
package_install
Findings (10)
References sudo — requests elevated privileges
DEPLOYMENT.md · code · sudo
apt-get install — installs system packages
DEPLOYMENT.md · code · apt-get install
Opens WebSocket connection
SOCIAL.md · code · WebSocket
Popular HTTP library — network access
INTEGRATION-EXAMPLES.md · code · node-fetch
POSTs data to external URL
INTEGRATION-EXAMPLES.md · code · .post(
"http://
References child_process — can spawn system processes
save-to-qdrant.js · prose · downgraded · child_process
fetch() — outbound network request
SKILL.md · code
Makes HTTP request to external URL
SKILL.md · code · fetch('http://
References agent configuration files
auth.js · prose · downgraded · agentConfig
Accesses sensitive environment variables
index.js · prose · downgraded · process.env.POLYGON_PRIVATE_KEY
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.
package_installnetwork_out Is this flag fair?
Thanks — recorded.