cv-resume
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting untrusted data provided by the user for the purpose of creating a formatted document.
- Ingestion points: User-provided personal contact details, work history, education records, and skill sets (outlined in Step 1 and the template in Step 5 of
SKILL.md). - Boundary markers: No specific delimiters or safety instructions are defined to separate user-provided content from the agent's instructional logic during interpolation into the HTML template.
- Capability inventory: The skill is restricted to generating HTML text output; it does not contain code for network operations (except for static font references), file system access, or command execution.
- Sanitization: The instructions do not specify sanitization or escaping requirements for user-provided strings before they are rendered into the final HTML output.
- [EXTERNAL_DOWNLOADS]: The generated HTML output references external design assets from a well-known service.
- Evidence: The template in
SKILL.mdincludes a CSS link tohttps://fonts.googleapis.com, which is used to fetch typography from the official Google Fonts repository.
Audit Metadata