brain
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read from and write to a local directory structure (
brain/). Because the agent is instructed to read these files to inform its behavior, there is a theoretical surface for indirect prompt injection if malicious content is introduced into the vault files. This is a low-risk architectural property of persistent memory skills. - [SAFE]: No malicious patterns, such as obfuscation, unauthorized network operations, or credential theft, were detected. The skill operates strictly within a local file system scope using provided tools.
Audit Metadata