openclaw-rl-training

Warn

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to clone code from a non-trusted repository: https://github.com/Gen-Verse/OpenClaw-RL.git.
  • [COMMAND_EXECUTION]: The skill includes an implementation example for a 'Terminal Agent' that uses subprocess.run(command, shell=True), which allows for arbitrary shell command execution based on model-generated output.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to train models using conversational feedback and trajectories, creating a significant attack surface for indirect prompt injection.
  • Ingestion points: Trajectories are collected in collect_rollouts.py and rollout_opd.py from live multi-turn conversations and user/environment feedback.
  • Boundary markers: No explicit boundary markers or 'ignore' instructions are visible in the provided snippets to delimit untrusted feedback data.
  • Capability inventory: The training process involves writing model checkpoints to the filesystem, while the associated agent examples demonstrate shell command execution (subprocess.run) and UI control (pyautogui).
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the feedback data before it is processed for training.
  • [DYNAMIC_EXECUTION]: The framework involves training and fine-tuning models (including LoRA adapters), which dynamically modifies executable model weights based on external data inputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 12, 2026, 06:50 PM
Security Audit — agent-trust-hub — openclaw-rl-training