starling-watch
Warn
Audited by Snyk on Mar 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Phase 2 "SENSE" explicitly requires using web search to find and ingest real conversations from public spaces (e.g., IndieWeb blogs, Bluesky/Mastodon/fediverse threads, community forums and personal site posts) and Phase 3/4 instructs the agent to interpret those signals into patterns and recommended actions for Grove, so untrusted third‑party content is read and can materially influence decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata