skill-installer
What this skill does
Install Codex skills from GitHub repositories into the $CODEX_HOME/skills directory.
github/openai - Data Exfiltration - 105.1k stars
Threat analysis
Skill info
pkg:github/openai/codex@7f928f6?skill=skill-installerAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/github_utils.py
The script uses the GITHUB_TOKEN or GH_TOKEN environment variables for authentication, which could be used to exfiltrate data if the token is compromised.Least Privilege
Least Privilege via local-llm-review
scripts/install-skill-from-github.py
The script uses subprocess.run with no explicit restrictions on the commands that can be executed, which could be a risk if the input is not properly sanitized.Badge
Add the Anomity scan badge for skill-installer 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-installer? Report an issue or request a rescan.
