apple-docs-index

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

• Third-party content exposure detected (high risk: 0.70). This skill's SKILL.md explicitly instructs the agent to fetch documentation from public web endpoints (e.g., https://sosumi.ai/documentation/{framework} and https://developer.apple.com/tutorials/data/index/{framework}), so the agent will read and act on open/public third‑party pages as part of its workflow, allowing those pages to influence tool use and next actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs fetching documentation at runtime from https://sosumi.ai/documentation/{framework} (and, as a fallback/index, https://developer.apple.com/tutorials/data/index/{framework}), which would be retrieved and injected into the agent's context to drive its responses, so these external URLs are runtime dependencies that can directly control prompts.