setup-matt-pocock-skills

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to read and act on user-generated issue content from third-party issue trackers (see issue-tracker-github.md: "Read an issue: gh issue view --comments" and issue-tracker-gitlab.md: "glab issue view --comments") and SKILL.md states that triage/to-issues/to-prd/etc. will read and use those issue bodies/comments to determine labels and next actions, so untrusted external content can materially influence behavior.