case-brief
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of legal opinions or casebook excerpts.
- Ingestion points: User-provided 'opinion text' or 'casebook excerpt' used as the basis for the summary.
- Boundary markers: Absent; the instructions do not require the use of delimiters or 'ignore' warnings for the input text.
- Capability inventory: The skill instructs the agent to save results to a 'Scratchpad connector' or other connected notes tools, which involves writing data to external services.
- Sanitization: Absent; the instructions do not specify any validation or sanitization of the input text before processing.
Audit Metadata