dir-organizer

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to use terminal tools and scripts to perform file system operations, including creating directories, moving files, and renaming them. While the skill includes a safety mechanism requiring user approval of a 'reconstruction plan' before execution, the underlying capability to modify the file system is sensitive.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for Indirect Prompt Injection. It ingests untrusted data from the local environment to function.
  • Ingestion points: Section 4.1 describes reading all file names and extensions in a directory. Section 4.4 describes scanning file contents to update internal links.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions embedded in the file names or content being processed.
  • Capability inventory: The agent has the capability to move, rename, and delete (clean) files based on its interpretation of the directory structure.
  • Sanitization: There is no mention of sanitizing or validating file names or content before they are used to generate the reorganization plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 12:46 PM