read-working-memory
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the vendor's nmem CLI tool and standard Unix commands to access working memory data. Evidence includes command examples such as
nmem --json wm readandcat ~/ai-now/memory.mdfound in SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external briefings and memory files, which represents a surface for indirect instructions. 1. Ingestion points: Data is retrieved from the nmem command output and the ~/ai-now/memory.md file as specified in SKILL.md. 2. Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are present in the provided skill content. 3. Capability inventory: The skill has the ability to execute the nmem CLI and read local files. 4. Sanitization: No sanitization or validation of the ingested memory content is documented within the skill.
Audit Metadata