The Agent Skills Directory

[SAFE]: The skill provides organizational conventions for file management and does not contain any executable scripts, network operations, or tool invocations.
[DATA_EXPOSURE]: It references environment variables for knowledge base and workspace directories ($MERIDIAN_CONTEXT_KB_DIR, $MERIDIAN_CONTEXT_WORK_DIR) to provide context for file operations, which is a standard functional requirement for writing-related tasks.
[PROMPT_INJECTION]: No patterns indicative of instruction overrides, safety bypasses, or system prompt extraction were found in the instructions.
[INDIRECT_PROMPT_INJECTION]: The skill advises reading external files like AGENTS.md for project structure. While this represents an ingestion point for external data, the skill itself lacks any tools or executable capabilities that could be exploited via injection.

writing-artifacts