emacsclient

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines how to use the Bash tool to execute emacsclient commands, which is the standard method for controlling a running Emacs process.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to interpolate paths and code into shell commands. This creates an attack surface where untrusted input could potentially influence the execution environment, though this is a common characteristic of tool-integration skills.
  • Ingestion points: Paths and Elisp snippets processed in SKILL.md.
  • Boundary markers: None provided in the instructions.
  • Capability inventory: Full shell access through the Bash tool and arbitrary Elisp evaluation via emacsclient as documented in SKILL.md.
  • Sanitization: The skill does not provide specific instructions for sanitizing or escaping the generated commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 02:27 PM
Security Audit — agent-trust-hub — emacsclient