app-store-review
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run various local shell commands, including plutil, grep, find, and sips, to inspect iOS project configuration files (Info.plist, .pbxproj) and source code for API usage and compliance markers.
- [EXTERNAL_DOWNLOADS]: The skill fetches updated privacy manifest keys, API categories, and guidelines from official Apple developer documentation sites (developer.apple.com) and Fastlane documentation. These are well-known technology service providers.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests and processes source code and strings files from an external project.
- Ingestion points: .swift, .m, .mm, .plist, and .pbxproj files within the project root.
- Boundary markers: None identified in the provided instructions.
- Capability inventory: File system read, command execution (grep, plutil, sips), and network access (curl).
- Sanitization: No explicit sanitization or filtering of processed file contents is mentioned before reporting to the user.
Audit Metadata