makepad-reference

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

• Third-party content exposure detected (high risk: 0.90). The skill's api-docs.md explicitly instructs the agent to use a WebFetch tool to retrieve and parse external public documentation (e.g., https://publish.obsidian.md/makepad-docs/ and GitHub repos), meaning the agent will fetch and interpret untrusted third‑party web content as part of its workflow.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent at runtime to use WebFetch to retrieve and extract content from external docs (for example: https://publish.obsidian.md/makepad-docs/DSL/Layout), which would be fetched and injected into the agent's prompt/context and thus can directly control agent behavior.