ClawAudit verdict
yiliu
AI-powered note-taking system using optional OpenAI API or local embeddings; explicitly documents no eval or arbitrary code execution, no hardcoded credentials, and local SQLite storage.
⚠ 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
credential_access
package_install
Findings (4)
Uses eval() — can execute arbitrary code
SKILL.md · frontmatter · eval(
Possible hardcoded credential
SKILL.md · code · API_KEY="your-api-key
Popular HTTP library — network access
package-lock.json · prose · downgraded · node-fetch
Accesses sensitive environment variables
src/ai/index.ts · prose · downgraded · process.env.OPENAI_API_KEY
Permissions & capabilities
No declared permissions — minimal attack surface.
package_installnetwork_incredential_access Is this flag fair?
Thanks — recorded.