ClawAudit verdict
finance-automation
The skill requires package installation, which could potentially be used for malicious purposes, but it seems to be intended for a legitimate finance automation purpose.
⚠ 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
package_install
Findings (5)
Accesses sensitive environment variables
ARCHITECTURE.md · code · process.env.STRIPE_WEBHOOK_SECRET
Popular HTTP library — network access
README.md · code · axios
References tunneling service
QUICKSTART.md · code · ngrok
Uses exec() — may execute shell commands
scripts/init-db.js · prose · downgraded · exec(
POSTs data to external URL
src/services/notification.js · prose · downgraded · .post(
`https://
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.