skills/lgbarn/skills/metal-sweep/Gen Agent Trust Hub

metal-sweep

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands including swift run and various Python scripts (analyze_results.py, multi_metric_rank.py, render_calmar_lists.py). It also instructs the agent to dynamically modify or create Metal kernel source code and register it in Swift source files before execution.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by interpolating user-provided strategy names and parameters directly into shell commands and source code files.
  • Ingestion points: User-supplied strategy names, parameter ranges, and file paths (e.g., <name>, <name>_sweep).
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions embedded in the user data.
  • Capability inventory: The skill possesses file-write capabilities (modifying .metal and main.swift) and shell execution capabilities (swift run, python).
  • Sanitization: No explicit sanitization or validation of the user-provided strategy names or parameters is performed before they are used in commands or code generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 03:29 PM
Security Audit — agent-trust-hub — metal-sweep