motion-system
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local filesystem to analyze the app's motion patterns and tone.
- Ingestion points: Reads project configuration files (
.xcodeproj,project.yml,.xcconfig,Package.swift) and Swift source files (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or specific instructions to ignore embedded prompts in the analyzed code.
- Capability inventory: The skill has the ability to write new Swift files and execute shell commands via
xcrun swiftc. - Sanitization: There is no mention of sanitizing or escaping the content read from the source files before processing.
- [COMMAND_EXECUTION]: The skill executes shell commands to verify the correctness of the generated code.
- Evidence: Uses
xcrun --sdk iphonesimulator swiftc -typecheckto validate the syntax and compatibility of the proposedMotion.swiftfile against the target iOS version. - [EXTERNAL_DOWNLOADS]: The skill references an external MCP server and specific design tools provided by the vendor.
- Evidence: Connects to
https://mcp.60fps.design/mcpand utilizes tools60fps_search_shotsand60fps_get_motion_codeto retrieve motion references from real-world applications.
Audit Metadata