extract-learnings
Fail
Audited by Snyk on Apr 9, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). This skill reads project and global files (MEMORY.md, CLAUDE.md, git logs) into agent prompts and emits proposed diffs/old-lines which would cause any secrets present in those files to be ingested by the LLM and potentially printed verbatim in outputs.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata