ito-cleanup

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill detects and executes shell commands defined in the project's configuration files (such as package.json, Rakefile, or Makefile) to run test suites. This behavior is a standard feature for development tools but relies on the integrity of the scripts defined within the project environment.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes untrusted source code and git diffs provided in the project context.
  • Ingestion points: Source code files, git change diffs, and project configuration files (e.g., CLAUDE.md).
  • Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to treat the ingested code content as data rather than instructions.
  • Capability inventory: The agent has the authority to modify files and execute local shell commands (testing scripts).
  • Sanitization: The skill does not describe any sanitization or validation logic for the code it cleans, relying instead on the model's inherent ability to parse programming languages.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 02:21 AM