dep-map

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 parses GitHub Issues via gh issue list / gh issue view and accepts Linear project URLs (see PHASE 0 / "For GitHub Issues" and "For Linear tickets"), meaning it ingests untrusted, user-generated content from public third-party sites that can directly influence analysis and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly fetches GitHub Issues at runtime using gh issue list / gh issue view (i.e. GitHub Issues URLs like https://github.com/.../issues/...) and accepts Linear project URLs (e.g. https://linear.app/...), and those fetched issue/ticket bodies are injected into the agent's analysis context—allowing remote content to directly control the agent's prompts/output.