guestbook-site

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates user-supplied data into its website generation process, representing a potential surface for indirect prompt injection.
  • Ingestion points: User input for site name and interaction fields (name, email, message) is collected in Step 1 and used in Step 2 of SKILL.md.
  • Boundary markers: No specific delimiters or instructions are used to isolate user-provided content from the website generation tool instructions.
  • Capability inventory: The skill utilizes tool create_website for site instantiation and tool read_file for internal instruction processing.
  • Sanitization: No input validation or sanitization of user strings is documented or performed prior to tool invocation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 07:33 AM