update-swiftui-apis
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes the Sosumi MCP tools (e.g.,
fetchAppleDocumentation,fetchExternalDocumentation) to ingest content from external websites at runtime. This creates a surface for Indirect Prompt Injection, where malicious instructions hidden in documentation or web pages could attempt to influence the agent's behavior during the file update or PR creation process.
Audit Metadata