The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a bundled Python script (validate_okf.py) to perform mechanical checks for OKF v0.1 conformance on local directories.
[SAFE]: Performs standard file system operations, such as creating directories and writing markdown files with YAML frontmatter, which are necessary for the skill's stated purpose of knowledge catalog management.
[SAFE]: References official documentation from the Google Cloud Platform GitHub repository for format specifications.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it reads and processes markdown content from potentially untrusted knowledge bundles.
Ingestion points: File reading logic in SKILL.md (Generate / refresh index.md) and the validate_okf.py script.
Boundary markers: No specific delimiters or safety instructions are defined to separate ingested bundle content from the agent's logic.
Capability inventory: The agent can write files and execute local validation scripts.
Sanitization: No explicit sanitization or content validation is performed on the descriptions extracted from concept files.

okf