cs-self-improving-agent
What this skill does
The skill is a self-improving agent for Claude Code that helps curate auto-memory into durable project knowledge. It allows users to review, promote, extract, and manage knowledge captured by Claude C
github/leoyeai - Security Misconfiguration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=cs-self-improving-agentAssessments (1)
Security Misconfiguration
Security Misconfiguration via local-llm-review
hooks/error-capture.sh
The script is designed to capture errors and potentially extract insights from them. While it is not explicitly malicious, it could be used to silently gather information about errors and system behavBadge
Add the Anomity scan badge for cs-self-improving-agent 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 cs-self-improving-agent? Report an issue or request a rescan.
