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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 06:13 AM
Issues
1