pm-image2proto

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context via the user-provided screenshot content and user follow-up modification instructions (Step 2 “Analyze the screenshot” and Step 4 “Handle modification requests”), which are not authored by the operating user.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's flowchart HTML template explicitly loads and executes remote JavaScript from the CDN URL https://cdnjs.cloudflare.com/ajax/libs/mermaid/10.9.0/mermaid.min.js at runtime, which is a required external dependency for rendering Mermaid diagrams.