ask-author
Warn
Audited by Snyk on Jun 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow (“materialize” / “prepare”) can fetch and summarize an outsider-authored tracked Issue from the repo’s issue tracker, and that issue body text is ingested into the agent’s LLM context via the “prepare → grill” path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata