local-file-manager

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to use shell commands such as cp, mkdir, and ls for file orchestration and provides instructions for executing Python scripts within a local virtual environment.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it ingests and processes untrusted data from user-provided files (PDF, PPTX, DOCX, XLSX).
  • Ingestion points: Untrusted data enters the agent context through files in the input/ directory.
  • Boundary markers: Absent; there are no specific delimiters or instructions to ignore potential commands embedded within the document content.
  • Capability inventory: Includes file system read/write access across ALL scripts and the ability to execute shell commands and Python scripts.
  • Sanitization: No evidence of content sanitization, validation, or escaping of external content is present in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 12:43 AM
Security Audit — agent-trust-hub — local-file-manager