i2r-nfr-authoring-mode
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill specifies the use of a local script (
scripts/i2r.py) via a shell command for artifact validation. This is a controlled execution of a project-internal tool used to verify data integrity. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files such as
04-functional.jsonand project documentation in theraw/folder. It implements strong mitigation measures by requiring all output to adhere to a strict JSON schema and by explicitly banning non-measurable or vague terminology, which limits the potential for external data to manipulate the agent's behavior.
Audit Metadata