Security audit
Security checks across malware telemetry and agentic risk
This evaluation skill is mostly coherent, but it needs review because it stores full evaluation conversations and includes a viewer that can automatically stop a local process on its port.
Install only if you are comfortable with evaluation transcripts and session histories being saved in the workspace. Avoid running it on sensitive or production conversations unless you control the output directory and retention. Be cautious with the HTML viewer: choose an unused port, and do not open untrusted spreadsheet/report artifacts in it.
#!/usr/bin/env python3 """ Extract conversation history from a completed session. Phase 3.3 tool: extract conversation history from a real session for context testing.
"""
Extract conversation history from a completed session.
Phase 3.3 tool: extract conversation history from a real session for context testing.
Usage:
python extract_session_history.py \def extract_history_from_session(session_key: str) -> list:
"""
Extract conversation history from a session.
Returns list of {"role": "user"|"assistant", "content": "..."}
"""def main():
parser = argparse.ArgumentParser(
description="Extract conversation history from OpenClaw session"
)
parser.add_argument(
"--session-key",64/64 vendors flagged this skill as clean.
Detected: suspicious.dynamic_code_execution