The Agent Skills Directory

[SAFE]: The skill defines a standard operational procedure for internal memory management. It utilizes the doctrine command-line utility for database maintenance tasks such as validation, record pruning, and relationship linking. No suspicious patterns, such as prompt injection, unauthorized data access, or external communication, were found.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from a memory corpus which could potentially contain instructions from external sources. * Ingestion points: The agent reads memories using doctrine memory validate, memory show, and memory search in SKILL.md. * Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the procedure. * Capability inventory: The agent can modify the corpus using doctrine memory edit and doctrine link as specified in SKILL.md. * Sanitization: No sanitization process is described for the content of the memories being reviewed.

dreaming