tidy-next-codebase

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is instructed to read and honor conventions from repository files such as .cursorrules, CLAUDE.md, and AGENTS.md. This creates a surface for indirect prompt injection where malicious instructions embedded in these files could influence the agent's behavior during the cleanup process.
  • Ingestion points: CLAUDE.md, AGENTS.md, .cursorrules, and documentation files within the target repository.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded malicious content are provided for these external files.
  • Capability inventory: The skill performs file system modifications (editing and deleting files) and executes shell commands.
  • Sanitization: No sanitization or validation is applied to the content processed from these configuration files.
  • [COMMAND_EXECUTION]: The skill automatically detects and runs scripts from the local package.json, such as typecheck, lint, test, and build commands. While these are necessary for the skill's purpose, they represent a vector for executing untrusted code if the project's build configuration is compromised.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 11:31 AM
Security Audit — agent-trust-hub — tidy-next-codebase