make-a-deck

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill architecture creates a surface for indirect prompt injection by processing untrusted user input to generate static HTML content.
  • Ingestion points: User-supplied topics, narrative outlines, and slide text (SKILL.md).
  • Boundary markers: The instructions lack requirements for delimiters or system-level warnings to distinguish user content from generated code.
  • Capability inventory: The skill has the capability to write HTML, JavaScript, and CSS files, and invokes tools such as gen_pptx and ask_user.
  • Sanitization: No sanitization or escaping procedures are defined for handling user input before it is interpolated into the final HTML document.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 12:43 PM
Security Audit — agent-trust-hub — make-a-deck