file-organizer

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use local shell commands such as ls, find, du, md5, mkdir, and mv. These commands are used to inspect file metadata, calculate hashes for duplicate detection, and reorganize the directory structure. These operations are consistent with the skill's stated purpose of file organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local file system, including file names and file type metadata. This creates a surface for indirect prompt injection if an attacker-controlled file name were designed to influence the agent's behavior. However, the skill mitigates this by requiring the agent to present an 'Organization Plan' and obtain explicit user approval before executing any modifications.
  • [DATA_EXFILTRATION]: While the skill reads file metadata and sizes to provide analysis, it lacks any network-enabled commands (e.g., curl, wget, ssh) to transmit this data to an external server. The data processing remains local to the user's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — file-organizer