comment-responder
Warn
Audited by Snyk on Jun 24, 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 skill’s runtime path ingests public comment text authored by other users (outsiders) via the “Ootto comment monitor” that detects each new comment and matches
match_textto decide whether to generate a reply/DM, so outsider free-form text is fed into the agent’s LLM context for matching/handling.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata