research
Warn
Audited by Snyk on Jul 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: 0.70). SKILL.md’s “External Research Workflow” explicitly allows “Search the codebase and external sources” and “Open and read the relevant source passages,” which at runtime can ingest outsider-authored free text from public web pages or other external sources into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata