social-x-post-card
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and renders user-supplied text (such as tweet bodies, handles, and metrics) directly into an HTML template, creating a surface for potential injection.
- Ingestion points: The skill takes untrusted text inputs, such as those shown in
example.md, to populate the card's content. - Boundary markers: There are no explicit instructions or delimiters mentioned to distinguish or isolate the user's data from the template's rendering logic.
- Capability inventory: The skill generates HTML and CSS that is rendered on a web surface and loads external scripts, which could be exploited if malicious content is injected.
- Sanitization: The skill's instructions lack requirements for sanitizing or escaping the user's input before interpolation into the HTML output.
- [EXTERNAL_DOWNLOADS]: The skill's template depends on assets fetched from well-known external service providers.
- Fetches the Tailwind CSS framework from
cdn.tailwindcss.comfor layout and styling. - Downloads typography from
fonts.googleapis.com.
Audit Metadata