axiom-optimize-build

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various local shell commands to analyze the development environment. It uses grep to search for build configurations within project.pbxproj, xcodebuild to execute builds and profile performance, and sysctl to retrieve system hardware specifications.
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection. Ingestion points: Content from project.pbxproj and Package.swift files, and the output from xcodebuild profiling. Boundary markers: None; the skill lacks delimiters or instructions for the agent to ignore commands potentially embedded in the ingested data. Capability inventory: In SKILL.md, the agent is directed to use grep, xcodebuild, sysctl, and sort to process project information and execution logs. Sanitization: None; data from external files and tool outputs is used directly in the agent's reasoning process.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 12:45 AM
Security Audit — agent-trust-hub — axiom-optimize-build