The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the nmem CLI tool to retrieve context and working memory data via commands such as nmem --json context and nmem --json wm read. These are legitimate operations used for context enrichment.
[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting data from external memory sources. 1. Ingestion points: Data is loaded from the nmem MCP server and CLI tool as described in SKILL.md. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the memory content as data rather than instructions. 3. Capability inventory: The skill utilizes shell command execution via the nmem utility. 4. Sanitization: No content filtering or validation is specified for the ingested data.

working-memory