Skills
skills/nonameplum/agent-skills/swift-package-manager/Gen Agent Trust Hub

swift-package-manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The documentation describes workflows where an agent interacts with untrusted project configuration files that could potentially contain malicious instructions. \n
  • Ingestion points: Package.swift manifest files and Package.resolved files (referenced in AddingDependencies.md and ResolvingPackageVersions.md). \n
  • Boundary markers: Absent in provided documentation examples. \n
  • Capability inventory: The skill describes the execution of high-impact commands such as swift build and swift run which compile and execute code (referenced in SwiftBuild.md and SwiftRun.md). \n
  • Sanitization: No sanitization of manifest content is described. \n- Persistence Mechanisms (LOW): Documentation in UsingShellCompletion.md provides instructions for users to add completion scripts to their shell profiles (e.g., ~/.bash_profile, ~/.zshrc). While modifying startup scripts is a common persistence technique, in this context, it is the standard and intended method for enabling shell auto-completion for the documented toolchain.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:04 PM