Skills
Navigate
skills/qu-skills/superpowers/email-design/Gen Agent Trust Hub

email-design

Warn

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to fetch installation instructions from a remote GitHub repository (inference-sh/skills).
  • [REMOTE_CODE_EXECUTION]: The skill uses npx to install a third-party command-line interface (belt-sh/cli) and leverages the belt tool to run remote applications (e.g., infsh/html-to-image). These operations involve downloading and running code from external, non-verified sources.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection.\n
  • Ingestion points: The skill takes user-provided prompts (e.g., in the belt app run commands) to generate images and banners.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided examples.\n
  • Capability inventory: The skill utilizes the Bash tool with access to the belt CLI, allowing it to execute network-connected applications.\n
  • Sanitization: No evidence of input sanitization or filtering was found in the skill's instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 02:19 PM
Security Audit — agent-trust-hub — email-design