ship
Warn
Audited by Snyk on Apr 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs the agent to run WebSearch in Step 2.5 ("Research best practices" with example queries) and to enable web_search_cached for Codex adversarial runs, meaning it fetches and reads public web search results/pages and uses those findings to decide frameworks and make workflow decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata