social-fetch
Warn
Audited by Snyk on Jul 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Yes—this skill fetches outsider-authored social post text from runtime network sources (e.g., public APIs/HTML via
agent-browseror scraped responses) and then parses/extracts it into the LLM-visible normalized fields liketext/thread/replies.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata