The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill performs legitimate documentation management tasks.
[COMMAND_EXECUTION]: The skill executes a local Python script (okf_init.py) to scaffold new bundles. The script uses safe path manipulation and standard libraries to generate markdown templates.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process markdown files from user-controlled repositories. 1. Ingestion points: Reads .md files within the .okf/ directory or specified bundle paths. 2. Boundary markers: Uses YAML frontmatter blocks and structural markdown headings to delineate data from metadata. 3. Capability inventory: The skill uses Read, Write, Edit, Grep, Glob, and Bash tools to manage files. 4. Sanitization: Content is processed as markdown documentation; the skill relies on the agent's internal safety filters for content handling.

okf