The Agent Skills Directory

[SAFE]: The skill's primary function is to maintain data quality and security. It explicitly directs the AI to remove passwords, tokens, and other authentication patterns from the memory store.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data (user memories) which creates a surface for indirect prompt injection.
Ingestion points: User-provided memories are loaded via memory_list and memory_search in SKILL.md.
Boundary markers: None; the agent processes the raw text of memories without specific delimiters.
Capability inventory: The skill has access to memory manipulation tools (memory_delete, memory_update, memory_add) but lacks network access or shell execution capabilities.
Sanitization: No explicit sanitization or filtering is performed on memory content prior to processing; the agent relies on its internal logic to perform the consolidation tasks.

memory-dream