semgrep-rule-creator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The SKILL.md workflow explicitly requires using WebFetch to read seven external Semgrep documentation links (e.g., raw.githubusercontent.com/... listed under "REQUIRED: Before writing any rule, use WebFetch to read all of these 7 links"), so the agent will fetch and interpret public third-party content that can materially influence its rule-generation actions.