threads
Warn
Audited by Snyk on Jul 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow can spawn Researcher threads that “inspect one external/source angle” and may ingest public web content fetched at runtime (outsider-authored free text) into the LLM context via the researcher evidence-gathering path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata