cowork-folder-organizer

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs local file management using standard tools like Read, Glob, Write, and Bash. All operations are scoped to a user-provided directory path.
  • [COMMAND_EXECUTION]: The skill uses Bash to rename and move files. Security risks are mitigated by the workflow which requires presenting a target folder tree and naming plan to the user for approval before any execution occurs. It also maintains a log (_organizer-log.md) for auditing and undoing operations.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it reads file headers and metadata during the inventory phase.
  • Ingestion points: The inventory workflow in SKILL.md reads headers and metadata from files.
  • Boundary markers: None explicitly defined in the prompt instructions.
  • Capability inventory: The skill has Write and Bash capabilities to modify the file system.
  • Sanitization: None specified for file content.
  • However, the risk is categorized as safe due to the human-in-the-loop requirement for the organizational plan and the policy of never deleting files outright.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:05 PM
Security Audit — agent-trust-hub — cowork-folder-organizer