persistent-memory-hygiene
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs standard local file operations to maintain an agent's task history and memory stores.
- [DATA_EXFILTRATION]: Accesses local paths in the
~/.openclawdirectory to manage internal state and session logs. This activity is restricted to the skill's own operational directory and does not involve network communication or data exfiltration. - [REMOTE_CODE_EXECUTION]: No remote scripts, external downloads, or dynamic execution patterns were identified in the skill instructions or configuration.
- [PROMPT_INJECTION]: The skill contains no instructions aimed at bypassing safety guidelines, overriding system prompts, or extracting sensitive configuration metadata.
Audit Metadata