The Agent Skills Directory

[COMMAND_EXECUTION]: Executes a local maintenance script plugins/ruflo-adr/scripts/verify.mjs using Node.js to analyze data graphs. This is a standard operation for the skill's stated purpose.
[PROMPT_INJECTION]: The skill processes data from memory namespaces, which is a potential surface for indirect prompt injection.
Ingestion points: Retrieves data from adr-patterns and adr-edges namespaces via memory tools.
Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the skill metadata.
Capability inventory: Use of Bash tool to execute node scripts.
Sanitization: The skill relies on the JavaScript script's logic for processing data rather than prompt-level sanitization.

adr-verify