review-audit
Fail
Audited by Snyk on Mar 25, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to extract and output verbatim quotes from user-provided reviews (collecting exact word-for-word phrases), so if any review contains secret values (API keys, tokens, passwords, cookies) the LLM would be required to reproduce them, enabling potential exfiltration.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata