skills/marswaveai/skills/explainer/Gen Agent Trust Hub

explainer

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell operations using the listenhub CLI to generate videos, manage authentication, and download files. It also utilizes standard utilities such as mkdir, echo, cat, and jq for managing its configuration settings in the .listenhub directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts free-text input for video topics and content, which is then interpolated into shell commands (e.g., --query "{topic}"). Since this data is processed by an external AI service via the CLI, it represents a surface for indirect prompt injection.
  • Ingestion points: User input collected during the Interaction Flow (Step 1).
  • Boundary markers: No explicit delimiters or boundary instructions are included in the command construction to isolate user content.
  • Capability inventory: The skill can execute shell commands, perform network operations through the listenhub binary, and write artifacts and configuration files to the local file system.
  • Sanitization: The skill does not perform validation or escaping on the user-provided topic before passing it to the CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:40 AM
Security Audit — agent-trust-hub — explainer