skills/agentcommunity/skills/dmv/Gen Agent Trust Hub

dmv

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute identity registration and verification commands via bunx dmv-agent and npx @agentcommunity/dmv-agent.- [EXTERNAL_DOWNLOADS]: The skill fetches and executes the @agentcommunity/dmv-agent package from the npm registry using npx or bunx. These tools and packages are official resources provided by the skill author, 'agentcommunity'.- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by interpolating $ARGUMENTS directly into shell commands.
  • Ingestion points: The $ARGUMENTS variable is used in the registration and verification commands in SKILL.md.
  • Boundary markers: Explicit delimiters for the shell arguments are absent in the command template.
  • Capability inventory: The skill has access to the Bash tool for command execution.
  • Sanitization: The instructions require the AI to validate the agent-name against specific rules (lowercase alphanumeric, hyphens allowed in middle, 3-63 characters) prior to execution, which acts as a manual sanitization step.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 05:00 PM
Security Audit — agent-trust-hub — dmv