resume-new
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches design assets and styling libraries from well-known service providers to format the generated resumes.
- Evidence: The design guide in
references/design-guide.mdincludes links to Tailwind CSS (cdn.tailwindcss.com), Font Awesome icons (cdnjs.cloudflare.com), and Google Fonts (fonts.googleapis.com). These are recognized well-known technology services. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes and embeds external user data directly into an HTML template without explicit sanitization or encoding instructions.
- Ingestion points: User-provided profile details such as name, contact information, and professional history defined in the collection steps of
SKILL.md. - Boundary markers: Absent; user input is directly interpolated into the HTML structure provided in the design guide.
- Capability inventory: The skill performs file writes to the local
html/directory as specified in the work flow ofSKILL.md. - Sanitization: No instructions for data validation or output encoding (e.g., HTML escaping) are present in the skill instructions.
- Mitigation: Sanitize all user-provided data and apply HTML escaping before interpolating content into the resume template.
Audit Metadata