pr-retro
Fail
Audited by Snyk on Mar 16, 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 explicitly instructs scanning diffs for hardcoded secrets and to report matching content snippets (and store them in the JSON snapshot), which would cause the LLM to read and output secret values verbatim.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata