scanned 1mo ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓
Self-Operating Computer Framework
The Self-Operating Computer Framework lets a multimodal model operate a real computer the way a person does: it captures screenshots, decides what to do, and issues mouse and keyboard actions to accomplish a stated objective. It's a compact, readable reference implementation of the "computer use" pattern that works across multiple vision-capable models.
Key features
Screen-perceive → reason → click/type loop driven by a vision LLM
Pluggable backends (GPT-4o, Gemini, Claude, LLaVA, and others)
Natural-language objectives: "open a browser and search for..."
Cross-platform desktop control (macOS, Windows, Linux)
Small, hackable codebase for building your own computer-use agent
A concrete starting point for GUI automation and computer-use experiments — useful for testing, repetitive desktop workflows, and research into agents that operate arbitrary software.
! Security: Review · 7575/100 · grade Bscanned 1mo ago
✓ no compromise signals8 risk-surface · 6/20 OWASP controls flagged
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
What this capability can do · med confidence (static)
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
OWASP Top 10 for LLM Applications
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.