excalidraw
Fail
Audited by Snyk on Apr 11, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The prompt explicitly instructs the agent to "preserve ALL text" from user-provided samples and reproduce it verbatim in shape labels, which would cause any secrets present in those samples (API keys, tokens, passwords) to be output by the LLM.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata