ClawAudit verdict
ai_daily_digest
daily-digest-ai
Fetches RSS feeds from tech blogs and uses an OpenAI-compatible API to score and generate a daily digest; credential_access is for OPENAI_API_KEY sent only to the configured LLM endpoint, which is the 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. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
credential_access
Findings (4)
Possible hardcoded credential
SKILL.md · code · API_KEY="<your-openai-compatible-key>
Uses exec() — may execute shell commands
scripts/digest.ts · prose · downgraded · exec(
String.fromCharCode — can build strings to evade detection
scripts/digest.ts · prose · downgraded · String.fromCharCode
Accesses sensitive environment variables
scripts/digest.ts · prose · downgraded · process.env.GEMINI_API_KEY
Permissions & capabilities
Requires 1 system binary.
credential_access Is this flag fair?
Thanks — recorded.