file-test-bug
Fail
Audited by Snyk on Mar 3, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt requires including the complete, unmodified contents of agent-metadata.md (log files) verbatim in the issue body, which could contain API keys, tokens, or other secrets and therefore forces the LLM to output secrets directly.
Audit Metadata