insight-from-chat
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its data processing workflow.
- Ingestion points: Untrusted data from user chat logs and feedback entries is inserted into the
Background Contextsection of the prompt defined inSKILL.md. - Boundary markers: There are no delimiters or explicit instructions to ignore embedded commands used to wrap the untrusted context.
- Capability inventory: The skill does not involve any dangerous actions such as network requests, file system modifications, or subprocess execution.
- Sanitization: No validation or sanitization is performed on the input data before it is passed to the language model.
Audit Metadata