full-audit
Fail
Audited by Snyk on Feb 28, 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 explicitly instructs subagents and the report assembler to read scanner/skill JSONs and include "notes" and findings verbatim in the final report — which will force the LLM to read and emit any hardcoded secrets or tokens those tools discovered.
Audit Metadata