skill-eval

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes external command-line tools (such as git and various AI agent adapters like claude or cursor-agent) via Node.js child_process modules to facilitate its evaluation workflow. This is a core part of its intended functionality as a developer tool.
  • Evidence includes the use of spawn and execFileSync in scripts/run-harness-eval.mjs and scripts/compute-eval-verdict.mjs to execute adapters and verify repository state.
  • [PROMPT_INJECTION]: As a tool that processes the output of other AI agents, it is naturally exposed to indirect prompt injection from evaluated artifacts.
  • Evidence: The skill reads and evaluates raw event streams and artifact files produced by sub-processes.
  • Sanitization: The skill mitigates this risk by using strict evidence verification with SHA-256 hashes, enforcing path isolation within the .skill-eval-runs/ directory, and instructing the agent to evaluate results based on deterministic assertions rather than surface-level formatting or claimed procedures.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 04:58 AM
Security Audit — agent-trust-hub — skill-eval