heal-skill
Fail
Audited by Snyk on Mar 5, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to read files and present exact before/after diffs and perform edits using exact old_string/new_string, which would force the agent to reproduce any file contents (including any embedded API keys or secrets) verbatim in its output if those files contain secrets.
Audit Metadata