gh-address-comments

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly runs scripts/fetch_comments.py (and gh api graphql) to fetch GitHub pull request comments, reviews, and review threads—user-generated content from public GitHub users—which the SKILL.md instructs the agent to read, summarize, and act on, so those untrusted third-party comments could inject instructions that influence actions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The prompt explicitly requests elevated network/sandbox permissions (e.g., "Run all gh commands with elevated network access" and "sandbox_permissions=require_escalated") which asks the agent to bypass or escalate sandbox/security controls, even though file edits themselves are project-specific.