deep-agent-review
Fail
Audited by Snyk on Feb 17, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The orchestrator explicitly instructs specialists to read code and save evidence including code snippets (e.g., auth-flow, tokens) into review files, which can force the LLM to emit verbatim secret values found in the repository.
Audit Metadata