starling-watch
Warn
Audited by Snyk on Oct 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to use web search and browse arbitrary online community spaces and conversations (such as Bluesky, Mastodon, and personal blogs) to mine content and sentiment, exposing the agent to outsider-authored free text via search results.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata