The Agent Skills Directory

[SAFE]: The skill performs legitimate memory management tasks using standard platform tools for fetching and modifying data.
[PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection as it processes and summarizes content stored in project memories which could originate from untrusted external sources.
Ingestion points: Content retrieved from the get_memories tool and local configuration files (.mem0.json, .mem0.md) as described in SKILL.md.
Boundary markers: No specific delimiters or safety instructions are defined to separate the fetched memory content from the agent's internal logic during analysis.
Capability inventory: The skill is authorized to perform add_memory, delete_memory, and search_memories operations.
Sanitization: No explicit content validation or sanitization is implemented for the data retrieved before it is processed by the agent.

mem0-dream