skills/marswaveai/skills/listenhub/Gen Agent Trust Hub

listenhub

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is configured to automatically install the @marswave/listenhub-cli package from the NPM registry if the listenhub binary is not present. This package is the core tool for the ListenHub ecosystem provided by the vendor.
  • [COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands to manage the ListenHub CLI, specifically listenhub auth status to verify credentials and listenhub auth login to initiate the authentication flow.
  • [INDIRECT_PROMPT_INJECTION]: As a router skill, it interprets user-provided natural language to select a destination skill. This creates a surface where untrusted data (the user prompt) influences the agent's logic flow, though the risks are mitigated by a defined routing table and the specific scope of the delegated tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:40 AM
Security Audit — agent-trust-hub — listenhub