skills/pionxzh/skills/codex-delegate/Gen Agent Trust Hub

codex-delegate

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from external repositories that may contain malicious instructions targeting the delegated AI worker.
  • Ingestion points: The delegated worker AI is configured to read files from the target repository directory, including specific instruction files such as AGENTS.md (scripts/codex_job.py).
  • Boundary markers: The skill prompt uses XML-style tags like <task> and <delegation_rules> to delineate instructions, which mitigates but does not fully prevent instruction confusion.
  • Capability inventory: The delegated worker has extensive capabilities including file system modification and shell command execution, especially when configured with the danger-full-access sandbox mode.
  • Sanitization: The skill includes an environment-based Git push block, though it is explicitly documented as a non-robust guardrail.
  • [COMMAND_EXECUTION]: The skill uses a Python helper script to execute the codex CLI tool.
  • Evidence: The scripts/codex_job.py script utilizes subprocess.Popen to execute codex commands with arguments supplied by the agent, such as directory paths and model configuration.
  • [DATA_EXFILTRATION]: The skill contains logic to prevent unauthorized data transmission via Git.
  • Evidence: The push_block_env function in scripts/codex_job.py attempts to disable Git pushes by rewriting push URLs in the process environment. The implementation is intended as a safety measure for the worker AI rather than a hardened security boundary.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 07:31 AM