i2r-acceptance-mode
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defined in SKILL.md executes a local validation script 'python scripts/i2r.py validate --stage 6'. This is an intended part of the development workflow to ensure the generated 06-acceptance.json file meets the project schema.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external source, 04-functional.json. Ingestion points: Functional requirement IDs and descriptions are read from 04-functional.json in step 1 of the execution flow. Boundary markers: The instructions do not specify explicit delimiters or instructions to ignore embedded directives in the input data. Capability inventory: The skill has file system write access (06-acceptance.json) and the ability to execute shell commands (i2r.py). Sanitization: The output is validated by the i2r.py script to ensure it conforms to the expected JSON schema, providing a structural check on the generated content.
Audit Metadata