claude-code-mastery

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: All provided Python tools, including the project analyzer and skill scaffolder, rely exclusively on the Python standard library, ensuring no external package vulnerabilities are introduced.
  • [COMMAND_EXECUTION]: The skill provides documentation for configuring lifecycle hooks and subagents which involves the execution of shell commands and external developer tools like formatters and linters. The scripts/skill_scaffolder.py tool properly sets executable permissions (0o755) on generated scripts.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from local CLAUDE.md files (ingestion point: scripts/claudemd_optimizer.py). Boundary markers: No specific delimiters or safety instructions are used to wrap the ingested content. Capability inventory: The skill contains scripts with file-write (scripts/skill_scaffolder.py) and directory-read (scripts/context_analyzer.py) capabilities. Sanitization: The tool uses regex-based analysis but does not perform sanitization of the input text for embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 01:51 PM