frontend-review-triage

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to run scripts/audit-triage.sh --repo <client-repo> and then read .../triage.json plus skim README.md and gh issue list ...—all of which are outsider-authored repository content and public issue text that can be ingested as readable strings into the LLM context.