ifrs
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The software review workflow in
feature-review.mdrequires the agent to ingest and analyze untrusted external data, specifically software implementation files and generated financial outputs such as invoices and balance sheets. - Ingestion points: Source code files, directories, and report artifacts provided by the user for compliance checking.
- Boundary markers: The instructions do not specify the use of delimiters or directives to ignore instructions that might be embedded within the analyzed content.
- Capability inventory: The agent is tasked with interpreting financial logic and generating compliance findings based on the provided inputs.
- Sanitization: There are no explicit instructions for sanitizing or escaping the untrusted file content before processing.
Audit Metadata