Skills
Navigate
skills/whytryharder/superpowers/social-media-carousel/Gen Agent Trust Hub

social-media-carousel

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the belt CLI via npx skills add belt-sh/cli and references setup documentation hosted on GitHub (inference-sh/skills).\n- [REMOTE_CODE_EXECUTION]: It utilizes the belt tool to invoke remote services like infsh/html-to-image and falai/flux-dev-lora to process content and generate visuals.\n- [COMMAND_EXECUTION]: The skill provides Bash scripts for local execution, including a batch processing loop to generate multiple carousel slides sequentially.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests user content to populate HTML templates for image generation. This creates an attack surface for indirect prompt injection where malicious data could target the image rendering service.\n
  • Ingestion points: User-provided text is inserted into the html field of the belt command in SKILL.md.\n
  • Boundary markers: Absent in the provided templates.\n
  • Capability inventory: Uses the Bash tool to perform network requests via the belt CLI.\n
  • Sanitization: No sanitization or escaping is implemented for user-injected content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 05:50 AM