generating-testimonial-quotes
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text from external sources such as reviews, social media, and emails, creating a surface for potential indirect prompt injection. Ingestion points: Customer feedback gathered in Step 1. Boundary markers: The skill does not define specific delimiters to isolate external content. Capability inventory: Focuses on text transformation; no dangerous tools or system commands are requested. Sanitization: No automated sanitization of the input text is provided.
Audit Metadata