faq-content-generator

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is text generation for ecommerce FAQs. It includes strict domain rules to prevent the invention of product facts or policies.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including product reviews and buyer questions, which presents a surface for indirect prompt injection.
  • Ingestion points: Reads product facts, buyer questions, reviews, policies, and support evidence provided by the user (SKILL.md).
  • Boundary markers: Includes instructions to 'Classify available evidence' and 'Remove duplicate, promotional, or unsupported questions' (SKILL.md).
  • Capability inventory: The skill has no capabilities to execute shell commands, perform network requests, or write to the filesystem.
  • Sanitization: Instructs the agent to never invent specifications or policies and to omit unsupported answers.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 05:39 AM
Security Audit — agent-trust-hub — faq-content-generator