spec-reviewer
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The prompt requires agents to return "evidence (file paths, code snippets...)" from the codebase, so if secrets are present in those snippets the LLM would be asked to include them verbatim, creating an exfiltration risk.
Audit Metadata