arinhub-verify-requirements-coverage

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

• Third-party content exposure detected (high risk: 1.00). This skill fetches and parses user-authored GitHub content (PR bodies, issue bodies, and diffs) via commands like "gh pr view", "gh issue view", and "gh pr diff" and uses that content to extract requirements and drive coverage decisions, exposing the agent to untrusted third-party input from public GitHub issues/PRs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill uses GitHub data fetched at runtime (e.g., via gh issue view / gh pr view which access URLs like https://github.com/owner/repo/issues/N or https://github.com/owner/repo/pull/123) and parses the issue/PR body into requirements that directly control the agent's prompts and analysis, so external content can influence agent behavior.