multi-lang-readme
Fail
Audited by Snyk on Feb 20, 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 read README.md including code blocks and reproduce them unchanged in translated output, which would force the LLM to emit any embedded secrets or API keys verbatim.
Audit Metadata