exa-hardened
Warn
Audited by Snyk on Apr 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly performs web searches and URL content extraction via Exa's APIs—see SKILL.md "Get Content" and the runtime scripts scripts/search.sh and scripts/content.sh—which causes the agent to fetch and ingest arbitrary public/untrusted third‑party web content (e.g., social posts, personal sites, public pages) that could contain instructions influencing its next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata