social-media-carousel

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines templates that interpolate user-controlled content into HTML and JSON structures for processing by external tools. Ingestion points: Slide text, hooks, and CTA content defined in the 'Carousel Structure' and 'Slide' sections of SKILL.md. Boundary markers: Absent; there are no delimiters or instructions to treat embedded content as untrusted. Capability inventory: The skill utilizes the belt app run command to process the generated HTML through remote applications. Sanitization: Absent; the examples demonstrate direct interpolation of strings into shell commands without escaping or validation.- [EXTERNAL_DOWNLOADS]: The skill references and requires external components for its functionality. Fetches installation guidelines from a public repository on GitHub (https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md). Recommends the installation of the belt-sh/cli package via npx.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:26 AM