matter-briefing
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Local Data Retrieval: The skill directs the agent to read case-specific markdown and YAML files from a defined local directory structure. This is a standard data processing task for summarizing legal records.
- [SAFE]: No Dangerous Capabilities: Analysis of the workflow shows no instructions for network access, external downloads, or shell command execution. The skill explicitly states it is read-only and does not perform write operations or strategy recommendations.
- [SAFE]: Logical Security Controls: The inclusion of a 'Conflict Gate' serves as a functional safety check, preventing the agent from generating summaries for unregistered cases and ensuring compliance with a predefined intake process.
- [SAFE]: No Injection or Obfuscation: The skill instructions are clear and do not contain patterns related to prompt injection, obfuscated URLs, or hidden malicious payloads.
Audit Metadata