best-practices-research
Warn
Audited by Snyk on Jul 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). SKILL.md requires dispatching subagents to run web research at runtime (via
web_search_exa/WebSearch/WebFetch), which necessarily ingests outsider-authored free text from fetched public web pages into the agents’ LLM context for summarization.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata