everything-search

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes external command-line tools, specifically the 'es' (Everything CLI) utility and PowerShell commands (Get-ChildItem), to perform file system operations.
  • [DATA_EXPOSURE]: The skill enables full-disk search capabilities, allowing the agent to locate files across the entire Windows file system, including sensitive user directories like Documents and potentially application data. While the instructions specify 'read-only' behavior, the capability itself provides significant visibility into the host file system.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The agent ingests file names and paths returned by the search commands (es and Get-ChildItem) into its context.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the results of the search (which may include attacker-controlled filenames) as untrusted data.
  • Capability inventory: The skill has the ability to execute CLI commands and PowerShell scripts to query the system.
  • Sanitization: There is no evidence of sanitization or filtering of the file metadata returned by the operating system before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:19 PM