triage
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: 0.80). The prompt requires the agent to present findings and copy their descriptions into todo files verbatim (including Problem Scenario and technical details), so if any finding contains credentials or tokens the agent would be expected to reproduce them in its output—creating an exfiltration risk.
Audit Metadata