computer-use-agents
What this skill does
A skill for building AI agents that interact with computers, covering computer use capabilities from Anthropic, OpenAI, and open-source alternatives. Focuses on perception-reasoning-action loops and v
github/sickn33 - Security Misconfiguration - 43.8k stars
Threat analysis
Skill info
pkg:github/sickn33/agentic-awesome-skills@11c9e67?skill=computer-use-agentsAssessments (1)
Security Misconfiguration
Security Misconfiguration via local-llm-review
SKILL.md
The skill's source code imports pyautogui and uses subprocess.run with shell=True, which could be used to execute arbitrary system commands if not properly sanitized. This is a potential risk if the aBadge
Add the Anomity scan badge for computer-use-agents to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of computer-use-agents? Report an issue or request a rescan.
