swift-concurrency-migration
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill explicitly directs the agent to execute shell commands such as
xcodebuild,xcrun, andswiftwithin the user's environment. These commands are used to identify compiler versions, deployment targets, and build settings (e.g.,SWIFT_STRICT_CONCURRENCY,SWIFT_DEFAULT_ACTOR_ISOLATION). These are standard diagnostic operations required for its stated purpose of project migration. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze and modify untrusted data provided by the user in the form of existing source code and project configuration files.
- Ingestion points: User-provided Swift source files (
.swift), Xcode project files (.xcodeproj), and Swift package manifests (Package.swift). - Boundary markers: The instructions do not mandate the use of delimiters or provide specific warnings to the agent to treat content within the processed code as non-authoritative data.
- Capability inventory: The agent has the ability to read local files, execute shell commands for build system inspection, and write changes back to the source code.
- Sanitization: There is no evidence of sanitization or validation logic to prevent malicious instructions embedded in comments or metadata within the user's codebase from being interpreted by the agent as legitimate task instructions.
Audit Metadata