jmb-improve-codebase-architecture
Fail
Audited by Snyk on Nov 21, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill's purpose is a local architecture review, and its file writes, browser opening, and CDN scripts are all disclosed and serve that purpose, but the Mermaid config sets
securityLevel: "loose", which weakens Mermaid's sanitization for an HTML report built from repository content, beyond what the task needs.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow reads local
git log --onelinecommit subjects to pick hot spots (SKILL.md:23), and commit messages can be authored by outside contributors whose PRs get merged, though an outsider cannot force delivery into this history.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata