canghe-infographic
Fail
Audited by Snyk on Feb 24, 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 mandates preserving all source data verbatim and writing user-provided content into generated files and prompts, so any secrets included in the source (API keys, tokens, passwords) would be emitted verbatim by the LLM, creating an exfiltration risk.
Audit Metadata