axiom-resolve-spm

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The skill recommends using swift build --disable-sandbox to resolve build failures related to Swift Macros. This command disables the security sandbox for the Swift compiler, which is designed to prevent potentially malicious code from accessing the system.
  • [REMOTE_CODE_EXECUTION]: The skill instructs the agent to execute commands that run package-defined code, such as swift build and swift test, and destructive commands like rm -rf ~/Library/Caches/org.swift.swiftpm. While standard for clearing Swift Package Manager caches, they involve the deletion of files in the user's home directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect injection surface. 1. Ingestion points: Package.swift, Package.resolved. 2. Boundary markers: Absent. 3. Capability inventory: swift build, swift test, rm -rf. 4. Sanitization: Absent. The skill reads and processes these external configuration files without explicit validation, which could allow a malicious package manifest to influence agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 09:50 PM
Security Audit — agent-trust-hub — axiom-resolve-spm