The Agent Skills Directory

[SAFE]: The skill implements a set of logical workflows for status transitions (e.g., active to archive) using high-level agent tools. No malicious patterns such as command execution, credential theft, or obfuscation were detected.- [PROMPT_INJECTION]: The skill was evaluated for potential indirect prompt injection vulnerabilities as it processes existing memory notes. Ingestion points: Notes are retrieved from the knowledge graph using search_notes. Boundary markers: The skill does not define specific delimiters to isolate user instructions from note content. Capability inventory: Uses move_note and edit_note to relocate files and update frontmatter metadata. Sanitization: No content sanitization is specified. The risk is considered minimal as the skill's operations are limited to internal organizational movements within a memory structure.

memory-lifecycle