The Agent Skills Directory

[SAFE]: The skill provides instructions for managing project documentation and memory layers. It focuses on reading local configuration files and updating documentation, which is a standard task for developer-oriented agents.- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by ingesting data from project files to maintain its memory layer.
Ingestion points: Reads .ai/*.md, package.json, requirements.txt, and schema.prisma from the local workspace.
Boundary markers: The instructions do not define specific delimiters for separating project data from system instructions.
Capability inventory: The skill is limited to reading and writing local project files; it does not perform network operations or execute shell commands.
Sanitization: No explicit sanitization or validation of the ingested file content is mentioned.

project-memory