user-story-implementer

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and reads GitHub Issue bodies via gh issue list/gh issue edit to obtain Acceptance Criteria (user-generated, potentially public content) which the agent must interpret to implement code and drive git/PR actions, so untrusted third-party content can directly influence its behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill uses the GitHub CLI at runtime (gh issue list) to fetch issue bodies from the repository via the GitHub Issues API (e.g., https://api.github.com/repos///issues), and those fetched Acceptance Criteria are then followed as instructions — so remote content directly controls agent prompts and is a required dependency.