cookbook-audit
What this skill does
Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.
github/anthropics - Dangerous Code Execution - 51.2k stars
Threat analysis
Skill info
pkg:github/anthropics/claude-cookbooks@f65eb12?skill=cookbook-auditAssessments (1)
Dangerous Code Execution
Dangerous Code Execution via local-llm-review
validate_notebook.py
subprocess.run(cmd, capture_output=True, text=True, check=True) # noqa: S603Badge
Add the Anomity scan badge for cookbook-audit 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 cookbook-audit? Report an issue or request a rescan.
