investigation-query
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of natural language instructions and documentation. There are no scripts, binary files, or network-enabled commands present. The behavior is consistent with the stated purpose of assisting legal investigations.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external investigation logs, which could contain adversarial instructions. * Ingestion points: Investigation logs provided as input to the /investigation-query command. * Boundary markers: The instructions lack explicit delimiters or instructions to ignore commands within the logs. * Capability inventory: Limited to information retrieval and logical analysis; no high-risk tools like code execution or network access are utilized. * Sanitization: No input filtering or escaping is implemented.
Audit Metadata