auto-bug-reporter

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to run mcp__github__search_issues against the public bobmatnyc/claude-mpm GitHub repo and read existing GitHub issues (user-generated public content) to decide whether to file or skip an issue, so untrusted third-party issue text can influence the agent's actions.