skills/openai/plugins/swiftpm-macos/Gen Agent Trust Hub

swiftpm-macos

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill is designed to interact with the Swift Package Manager by executing commands such as swift build, swift run, and swift test. These operations are essential for its function as a development tool, though they involve running compiled code within the environment.
  • Indirect Prompt Injection Surface: The skill reads the Package.swift file to identify products and targets. Because this file is external and could be modified by third parties, it represents a potential ingestion point for untrusted data.
  • Ingestion points: Package.swift (referenced in SKILL.md).
  • Boundary markers: No specific delimiters or warnings for embedded instructions are defined in the workflow.
  • Capability inventory: The skill possesses the ability to build and execute binaries via the swift command-line interface.
  • Sanitization: The instructions do not specify validation or sanitization of the package manifest content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:17 PM
Security Audit — agent-trust-hub — swiftpm-macos