specialist-product-feedback-synthesizer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by interpolating untrusted user input directly into the prompt of a sub-agent without proper encapsulation or instructions to treat the input as data.
- Ingestion points: The variable
{the_user_question}is used inSKILL.mdas the final part of the sub-agent's prompt, making it the primary entry point for untrusted data. - Boundary markers: There are no delimiters (such as XML tags or triple quotes) or specific instructions to the model to ignore potential commands contained within the user question.
- Capability inventory: The spawned agent is instructed to perform tasks including data ingestion, API integration, and competitive feedback mining, which could be leveraged if a user successfully injects malicious instructions.
- Sanitization: There is no evidence of sanitization, validation, or filtering applied to the user input before it is passed into the sub-agent context.
Audit Metadata