The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using Node.js to run a local script (kb.js) with various arguments (scan, apply, lint, index, stats). This is the core functionality for managing the knowledge base folder.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection through its data ingestion workflow.
Ingestion points: The scan and apply operations ingest new materials from external sources such as claude-docs (referenced in SKILL.md).
Boundary markers: No specific delimiters or instruction-ignore markers are defined to separate ingested data from agent instructions.
Capability inventory: The skill possesses the capability to execute shell commands via node and modify the local filesystem within the knowledge base directory.
Sanitization: There is no evidence of content sanitization or validation before the external materials are processed or indexed.
[SAFE]: No indicators of data exfiltration, hardcoded credentials, or obfuscated code were found in the skill's instructions. The use of local scripts and relative paths follows standard development practices.

kb