read-working-memory
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
nmemcommand-line utility with specific flags to retrieve session context in JSON format. - [COMMAND_EXECUTION]: The skill uses standard shell commands (
testandcat) to access a fallback file at~/ai-now/memory.mdfor legacy configurations. - [SAFE]: The skill ingests data from local memory stores, representing an indirect prompt injection surface. Ingestion points: Output from the
nmemtool and content from~/ai-now/memory.md. Boundary markers: The skill does not define specific delimiters for the ingested context. Capability inventory: The skill is restricted to local command execution and file reads. Sanitization: No content validation or escaping is applied to the retrieved memory data. This behavior is expected for context-loading functionality.
Audit Metadata