social-media
Warn
Audited by Snyk on Mar 17, 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 SKILL.md "Repurposing" section and the "How to Use" examples (and README) explicitly instruct the agent to accept and extract content from blog/article URLs or pasted article text (e.g., "[paste URL or article text]"), meaning it will fetch/ingest untrusted public web/user-generated content and act on it to generate posts.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata