file-search

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The skill documents installation procedures using sudo with system package managers such as dnf, apt, and pacman. This is standard administrative behavior for installing system-level dependencies.
  • [COMMAND_EXECUTION]: The skill provides a variety of command-line examples for using the fd and rg tools to interact with the local file system.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read file names and content, which introduces a potential attack surface if the files being searched contain malicious instructions meant to influence the AI agent's behavior.
  • Ingestion points: Command output from fd (file names) and rg (file content) entering the agent's context.
  • Boundary markers: None specified in the skill instructions.
  • Capability inventory: File system metadata and content retrieval via shell commands.
  • Sanitization: No explicit sanitization or filtering of file content is provided within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 07:41 AM