ai-md
What this skill does
AI.MD is a tool for converting human-written system prompts (like CLAUDE.md) into a structured format that AI models follow more reliably and with fewer tokens. It is a methodology for improving AI co
github/leoyeai - Excessive Agency - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=ai-mdAssessments (2)
Excessive Agency
Excessive Agency via local-llm-review
examples/after.md
GATE-1 restate: trigger: new-task → action: first-sentence="What you want me to do is ___"Privilege Escalation
Privilege Escalation via local-llm-review
examples/after.md
GATE-2 protect-files: trigger: .env / docker-compose* / package.json → action: line-1="Backing up first." + cp file file.bakBadge
Add the Anomity scan badge for ai-md 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 ai-md? Report an issue or request a rescan.
