research-platform
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill’s runtime path can fetch public web content for benchmarks via the benchmark-agent’s WebSearch/WebFetch, and that fetched outsider-authored text is ingested into the LLM context as benchmark context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata