showcase-export
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: 1.00). This skill forces the agent to narrate invisible skill instructions, reconstructed tool calls and exact command/tool usage (including "Tool calls made" and bash/DB operations), which would require or strongly incentivize reproducing any embedded API keys, tokens, or passwords verbatim in the transcript.
Audit Metadata