company-research
Warn
Audited by Snyk on Jul 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md requires using Exa Agent /
web_search_advanced_exato fetch public web content at runtime and then ingestagent_get_run_output’soutput.text/output.structured(withoutput.groundingcitations) into the agent’s LLM context, which is outsider-authored free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata