desktop-commander

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes tools like mcp__desktop-commander__start_process to run shell commands and manage terminal sessions. It includes a specific warning that terminal commands can access files outside of restricted directories.
  • [DATA_EXFILTRATION]: It features tools to read local files and external URLs, which provides a capability to access potentially sensitive data.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and processes data from untrusted local files and remote URLs.
  • Ingestion points: Data is ingested via read_file, read_multiple_files, and start_search as documented in SKILL.md.
  • Boundary markers: No delimiters or isolation instructions are provided to separate untrusted data from the agent's instructions.
  • Capability inventory: The skill possesses powerful capabilities including file modification and terminal execution as listed in references/desktop-commander.md.
  • Sanitization: No sanitization or validation mechanisms are defined for the processed content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 09:31 AM