pr-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and read GitHub PR title and body (e.g., via "gh pr view PR_NUMBER --json number,title,body" in SKILL.md and SPEC.md), which are user-generated, public/untrusted third-party content the agent must interpret and which can directly influence whether it rewrites or updates PRs.