The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to retrieve and process persistent data from the Supermemory MCP, creating a surface for indirect prompt injection. If malicious instructions are stored in the memory database from prior interactions or external research, they could be executed when the agent recalls that context.
Ingestion points: The supermemory tool's search, list, and profile modes (SKILL.md).
Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within retrieved memories.
Capability inventory: While the skill focuses on memory management, the retrieved data is passed to the main agent which may possess broader capabilities such as file system access or command execution.
Sanitization: No sanitization, validation, or filtering of the retrieved memory content is described in the workflow.

supermemory