reviewing-pull-requests

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

• Third-party content exposure detected (high risk: 0.90). This skill directly fetches and interprets user-generated GitHub PR data (e.g., via gh pr view, gh pr diff, and similar calls in scripts/pr-manager.py and scripts/quality-gates.sh and the SKILL.md workflows) and uses that content to drive labeling, reviewer assignment, quality checks, and merge decisions, which exposes the agent to untrusted third-party content that could carry indirect prompt-injection.