x-skill
Warn
Audited by Snyk on Jun 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: 0.85). Outsider free text can enter the LLM context via runtime API responses from X endpoints (e.g.,
xurl read,search,timeline,mentions,dms) where the returned JSON includes post/user-authoredtextfields that the agent would ingest.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata