build-feature
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to an official Model Context Protocol (MCP) server at
https://api.shipswift.app/mcpto fetch extended component recipes and guides. This targets the vendor's own infrastructure for intended functionality.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads external code files to guide code generation, creating a surface where instructions embedded in those files could influence agent behavior.\n - Ingestion points: Reads Swift source files from
ShipSwift/SWPackage/and the component catalog fromskills/catalog.md.\n - Boundary markers: No specific delimiters or safety instructions are defined to wrap or isolate the ingested source code content.\n
- Capability inventory: The agent uses ingested data to perform code generation, adapt patterns, and list project dependencies.\n
- Sanitization: No sanitization or validation of the file content is performed before it is used for prompt interpolation.
Audit Metadata