The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent on how to execute mem0 CLI commands in the terminal to manage memories. This includes adding, searching, listing, updating, and deleting data. The skill provides clear instructions on command usage and flag combinations.
[EXTERNAL_DOWNLOADS]: The skill recommends installing external packages: @mem0/cli via npm and mem0-cli via pip. These are official vendor resources belonging to 'mem0ai' and are used to provide the primary functionality of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill retrieves data from the Mem0 platform that may contain instructions written by an attacker (Indirect Prompt Injection surface).
Ingestion points: Data enters the agent's context through commands that retrieve memories, such as mem0 search, mem0 list, and mem0 get (referenced in SKILL.md and references/command-reference.md).
Boundary markers: The instructions do not specify any boundary markers or delimiters (like XML tags or markdown blocks) to isolate retrieved memory content from the agent's instructions.
Capability inventory: The agent has the capability to execute shell commands (mem0 CLI), write to the terminal, and potentially perform other tasks based on the retrieved content.
Sanitization: There is no mention of sanitizing or filtering retrieved content before it is processed by the agent.

mem0-cli