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's Documentation section explicitly requires using WebFetch to read four external public links (e.g., semgrep.dev docs, appsec.guide, and a GitHub docs tree), so the agent will fetch and interpret untrusted third-party web content as part of its required workflow.