linyuebanzi-video-cover-generator

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a reference portrait from a remote server (r2.cloudnative101.net) to maintain visual consistency in generated images. This is a documented part of the workflow.
  • [COMMAND_EXECUTION]: The skill provides instructions for executing a specific Python script (generate.py) located in an external directory (linyuebanzi-image-gen). This script is used to interface with the MuleRun API for image generation.
  • [CREDENTIALS_UNSAFE]: The skill documentation refers to the use of an API key stored in an environment variable (MULERUN_API_KEY). This is a recommended security practice for handling secrets rather than hardcoding them within the skill files.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted user video scripts for prompt distillation. Ingestion points: User video script input. Boundary markers: Absent. Capabilities: External command execution via generate.py. Sanitization: Keyword blocklist in references/blocklist.txt.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:04 AM
Security Audit — agent-trust-hub — linyuebanzi-video-cover-generator