skill-creator
What this skill does
Skill creation and management tool for extending Codex's capabilities with specialized knowledge, workflows, and tool integrations.
github/openai - Rogue Agent - 105.1k stars
Threat analysis
Skill info
pkg:github/openai/codex@7f928f6?skill=skill-creatorAssessments (2)
Rogue Agent
Rogue Agent via local-llm-review
scripts/init_skill.py
The script allows creation of new skills with potential for malicious content. It includes parameters like --resources and --examples that could be exploited to inject harmful code or data.Least Privilege
Least Privilege via local-llm-review
scripts/quick_validate.py
The script validates skill metadata but does not enforce strict least privilege checks on the content or capabilities of the skill itself.Badge
Add the Anomity scan badge for skill-creator 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 skill-creator? Report an issue or request a rescan.
