research-content
Warn
Audited by Snyk on Mar 5, 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 explicitly instructs the agent to gather and analyze content "across Twitter/X, GitHub, social media, and blogs" and to "Use WebSearch to find" trending topics and key accounts in Step 2 of SKILL.md, which clearly requires fetching and interpreting untrusted public user-generated web/social content that can influence subsequent actions.
Audit Metadata