Security audit
Security checks across malware telemetry and agentic risk
The skill locally analyzes user-provided ChatGPT exports to create a profile, which is sensitive but disclosed, user-controlled, and not shown to upload, hide, or automatically modify anything.
Install only if you are comfortable analyzing your ChatGPT export locally. Treat conversations.json, generated profiles, and prompt snippets as sensitive personal files; review, redact, and minimize them before adding anything to SOUL.md, AGENTS.md, repositories, or hosted agents. Use a virtual environment and consider pinning dependencies. Do not run test_wildchat.py unless you intentionally want to fetch and profile the external WildChat dataset.
# Install with: pip install -r requirements-test.txt # Core skill requirements (from requirements.txt) scikit-learn>=1.3.0 numpy>=1.24.0 PyYAML>=6.0
# Core skill requirements (from requirements.txt) scikit-learn>=1.3.0 numpy>=1.24.0 PyYAML>=6.0 # WildChat dataset access
# Core skill requirements (from requirements.txt) scikit-learn>=1.3.0 numpy>=1.24.0 PyYAML>=6.0 # WildChat dataset access datasets>=2.14.0
PyYAML>=6.0 # WildChat dataset access datasets>=2.14.0 # Optional: For faster streaming # pyarrow>=12.0.0
# Core dependencies scikit-learn>=1.3.0 numpy>=1.24.0 PyYAML>=6.0
# Core dependencies scikit-learn>=1.3.0 numpy>=1.24.0 PyYAML>=6.0 # Optional: For advanced BM25 ranking (script has built-in fallback)
# Core dependencies scikit-learn>=1.3.0 numpy>=1.24.0 PyYAML>=6.0 # Optional: For advanced BM25 ranking (script has built-in fallback) # rank-bm25>=0.2.2
55/55 vendors flagged this skill as clean.
No suspicious patterns detected.
