regression-suite
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md requires reading multiple outsider-authored markdown files at runtime—e.g.,
production/qa/bugs/*.md(closed/fixed bug descriptions) anddesign/gdd/systems-index.mdplus per-system GDD files—then uses their extracted free text (acceptance criteria, edge cases, fix descriptions) to generate the report/manifest in the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata