swift-package-manager
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard Swift development tools (
swift build,swift test,swift package) to verify package integrity. These are necessary for the skill's primary function. - [INDIRECT_PROMPT_INJECTION]: The skill reads external data from package manifests and source files to drive build and test commands, which is a standard surface for build-system management.
- Ingestion points: The skill reads
Package.swift,Package.resolved, source/test/resource layout, and generated code (documented inSKILL.md). - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined between manifest content and agent instructions.
- Capability inventory: The skill executes
swift build,swift test, andswift packagecommands (documented inSKILL.md). - Sanitization: No explicit sanitization of manifest logic or source content is implemented before execution.
Audit Metadata