setup-bmal-skills

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs other skills to fetch and read GitHub/GitLab issues and their comments (see issue-tracker-github.md and issue-tracker-gitlab.md — e.g., "gh issue view --comments" / "glab issue view --comments"), which are untrusted, user-generated third-party content that the agent is expected to interpret and act on, so malicious instructions in those tickets could influence tool use and decisions.