sop-authoring

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Example 1: Code Review SOP" explicitly instructs the agent to "Fetch pull request details from {pr_url}" and to read PR descriptions and changed files, which requires ingesting untrusted, user-generated content from arbitrary/public URLs (pull requests), enabling indirect prompt injection.