The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes external documentation files and metadata, creating a surface for indirect prompt injection where malicious content within those files could influence agent behavior.
Ingestion points: Reads Markdown documentation from embedded-docs/ and structured data from exports/ (SKILL.md).
Boundary markers: Absent; the instructions do not define delimiters or provide warnings to ignore embedded instructions in the ingested data.
Capability inventory: Includes the ability to write to the file system, execute shell commands, and run Python scripts (SKILL.md).
Sanitization: None; the skill does not perform any validation or sanitization of the input content before processing.
[COMMAND_EXECUTION]: The skill uses shell commands and dynamic Python execution for file management and quality auditing tasks.
Shell commands: Uses find, rg (ripgrep), and wc for file discovery and counting.
Dynamic execution: Utilizes python3 -c to execute inline Python scripts that parse JSON files and validate content fields.

node-docs