The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external Markdown files to retrieve rules and guidance, which creates a surface for indirect prompt injection where malicious instructions embedded in the knowledge base could influence agent behavior.
Ingestion points: The irudd-okf read and rg commands are used to fetch content from repository or personal files.
Boundary markers: The skill does not specify the use of delimiters or warnings to ignore instructions found within the processed files.
Capability inventory: The agent is empowered to read files, write files (irudd-okf write), and is explicitly instructed to "apply the retrieved guidance."
Sanitization: There is no evidence of sanitization or validation of the retrieved Markdown content before it is interpolated into the agent's context.
[COMMAND_EXECUTION]: The skill relies on shell commands for its core functionality, specifically the irudd-okf CLI and the standard rg (ripgrep) utility, which execute within the local environment.

okf