dd-cli-usage

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a guide for the agent to interact with a command-line tool named dd-cli. It instructs the agent to use --help flags to discover capabilities, which is a standard and safe operational procedure.
  • [COMMAND_EXECUTION]: The skill requires the execution of dd-cli on the host system. This is the primary intended purpose of the skill and does not include any arbitrary or suspicious command patterns.
  • [INDIRECT_PROMPT_INJECTION]: The agent processes output from the dd-cli tool, which may include data from external DoorDash services (like store names or item descriptions).
  • Ingestion points: The agent reads the standard output of dd-cli commands (SKILL.md).
  • Boundary markers: No explicit delimiters or safety instructions are provided to the agent for handling the tool output.
  • Capability inventory: The agent can execute various dd-cli subcommands to interact with the DoorDash platform.
  • Sanitization: No specific filtering or sanitization of the tool's output is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 05:23 PM
Security Audit — agent-trust-hub — dd-cli-usage