setup-matt-pocock-skills

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly configures agent workflows to read and act on user-generated issue tracker content (see SKILL.md and issue-tracker-github.md / issue-tracker-gitlab.md which instruct using "gh issue view ... --comments" or "glab issue view ... --comments"), so untrusted issue bodies/comments from GitHub/GitLab can be ingested and influence triage and other agent actions.