find-people
Warn
Audited by Snyk on Apr 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and acts on user-generated social content (e.g., LinkedIn profile URLs and engagement/posts) via the Competitor Engagement/Activity and social-listening signals — the workflow (SKILL.md Steps 3–5 and the signal deploy descriptions) shows the agent reads API-returned results derived from public LinkedIn posts/engagement and may base deployments or follow-up actions on that content, exposing it to untrusted third-party input.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata