github-project-management

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated GitHub content (issue bodies, comments, issue lists and project data via commands like gh issue view, gh issue list, gh issue comment, and gh project item-list) and feeds that content into automation (e.g., npx ruv-swarm github analyze-stale, issue-decompose, triage) that makes decisions and performs actions (closing/editing issues, assigning labels, moving cards), so untrusted third-party content can materially influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill repeatedly runs npx ruv-swarm at runtime (associated repo https://github.com/ruvnet/ruv-swarm), which fetches and executes remote package code that generates/decomposes tasks and thus directly controls prompts/instructions and is a required runtime dependency.