research
Warn
Audited by Snyk on Jun 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill’s workflow explicitly requires “web-first” research with “real source URLs” and “search the live web,” meaning runtime-fetched public web pages (outsider-authored free text) are ingested into the agent’s LLM context during the Research step.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata