plan-ceo-review
Warn
Audited by Snyk on May 3, 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). The skill's required workflow explicitly uses WebSearch in the "Landscape Check" step and invokes an external codex exec with web_search_cached in the "Outside Voice" flow (and may open arbitrary external URLs), so it fetches and ingests open/public web content which the agent is expected to read and incorporate into planning decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata