cookbook-audit

Warn

Audited by Runlayer on Feb 24, 2026

Risk Level: MEDIUM
Scan Summary
Max Score
76%
Files
4
Flagged
4
Chunks
6
Flagged Files (4)
.gitignoreHIGH
76.3%

Malicious tool definition detected

Tool: .gitignore Description: # Temporary files generated during notebook review

SKILL.mdHIGH
76.3%

Malicious tool definition detected

Tool: SKILL.md [1/2] Description: --- name: cookbook-audit description: Audit an Anthropic Cookbook notebook based on a rubric.

Tool: SKILL.md [2/2] Description: cookbooks, and direct users to the Academy to learn more on topics.

style_guide.mdHIGH
76.3%

Malicious tool definition detected

Tool: style_guide.md Description: # 1. Introduction Purpose: Frame the notebook around the problem being solved and the value delivered, not the machinery being built.

validate_notebook.pyHIGH
76.3%

Malicious tool definition detected

Tool: validate_notebook.py [1/2] Description: #!/usr/bin/env python3 # /// script # requires-python = ">=3.12" # dependencies = [ # "nbconvert", # ] # /// """ Automated validation checks for Anthropic Cookbook notebooks.

Tool: validate_notebook.py [2/2] Description: not found_constant: # Check if there are any model references at all has_model_refs = False for cell in self.cells: if cell.get("cell_type") != "code": continue source = self.get_cell_source(cell) if re.search(r'["\']claude-', source): has_model_refs = True break if has_model_refs: self.warnings.append( "Model name should be defined as a constant at the top of the notebook " "(e.g., MODEL = 'claude-sonnet-4-6') to make future updates easier" ) def ch

Audit Metadata
Max File Score
76%
Classification
UNKNOWN_SERVER
Files Scanned
4
Files Flagged
4
Chunks Analyzed
6
Analyzed
Feb 24, 2026, 11:34 PM
Security Audit — runlayer — cookbook-audit