presentation
Warn
Audited by Snyk on Jul 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required runtime workflow reads the spec’s markdown from
tech-specs/<slug>/*.md(outsider-authored spec content) and injects it into the LLM context via the deck-generation “Deep ingest” phase (Phase 1/1b) where the skill “reads … in full” and uses it to plan and generate slide content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata