create-agent-skills
What this skill does
This skill provides guidance on creating, writing, building, and refining Claude Code Skills. It is a teaching/development tool for authoring skills, not an execution tool itself.
github/glittercowboy - Security Misconfiguration - 2k stars
Threat analysis
Skill info
pkg:github/glittercowboy/taches-cc-resources@1757615?skill=create-agent-skillsAssessments (1)
Security Misconfiguration
Security Misconfiguration via local-llm-review
references/api-security.md
The skill recommends using `~/.claude/scripts/secure-api.sh` as a wrapper for API calls, but the script itself is not shown. If this script is not properly implemented (e.g., if it does not securely lBadge
Add the Anomity scan badge for create-agent-skills 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 create-agent-skills? Report an issue or request a rescan.
