clarify
Fail
Audited by Snyk on Feb 13, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to record and echo the original requirement verbatim into a state file and final summary, so any API keys/passwords included in the requirement would be output and stored by the LLM, creating an exfiltration risk.
Audit Metadata