audit-memory
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious intent, obfuscation, or data exfiltration patterns were identified. The skill's primary purpose is local maintenance, and it explicitly instructs the agent to never auto-delete content without user review.
- [COMMAND_EXECUTION]: The skill utilizes tools to interact with the local file system, including reading file contents, updating file timestamps (utime), and deleting outdated memory drawers. These operations are restricted to the management of the agent's own data stores and include instructions for user oversight.
- [DATA_EXFILTRATION]: The skill mentions extracting URLs from local memory for verification. It includes a caution regarding the use of web fetching tools, noting the potential cost and advising the agent to obtain user permission before attempting to access external links.
Audit Metadata