darwin-skill
What this skill does
An AI agent skill for optimizing and evaluating other AI agent skills, inspired by autoresearch and integrating Microsoft Research's SkillLens and SkillOpt frameworks.
github/alchaincyf - Tool Misuse - 5.4k stars
Threat analysis
Skill info
pkg:github/alchaincyf/darwin-skill@2fbaf41?skill=darwin-skillAssessments (1)
Tool Misuse
Tool Misuse via local-llm-review
scripts/screenshot.mjs
The script uses `execSync` to run external commands (e.g., `npm install -g playwright-core` and `npx playwright install chromium`). This could be a risk if the script is executed in an environment wheBadge
Add the Anomity scan badge for darwin-skill 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 darwin-skill? Report an issue or request a rescan.
