product-roadmap
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). SKILL.md Step 3–5 uses the GitHub adapter to harvest outsider-authored issue/PR/ milestone description bodies (including
body/title/comments) viagh issue list/gh pr list, then runs theintakeskill over that harvested text, which is then fed into the agent’s LLM context for node creation and later assembly/rendering.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata