efficient-frontier
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 (medium risk: 0.65). The skill’s workflow explicitly delegates “research scans” and “browser/testing passes,” which at runtime can cause subagents to fetch and ingest outsider-authored free text from public web pages/URLs into the LLM context (indirect prompt injection risk).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata