The Agent Skills Directory

[SAFE]: The skill follows security best practices for secret management by retrieving API credentials (KLING_ACCESS_KEY, KLING_SECRET_KEY, KLINGAI_API_KEY) from environment variables rather than hardcoding them.
[SAFE]: All network requests are directed to the official Kling AI API domain (api.klingai.com), and external links point to the author's official domains or project sites.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API responses to track task status and results. This constitutes an ingestion surface for potentially untrusted data if the API source were compromised, though the risk is limited to data display.
Ingestion points: Data returned from requests.get calls in SKILL.md (poll_task, update_all) and references/job-tracker-class.md (refresh_job).
Boundary markers: Absent; the skill directly processes and prints status messages and metadata from the API.
Capability inventory: The skill uses requests for network access and os for environment access. The platform configuration restricts tools to Read, Write, Edit, Bash(npm:*), and Grep.
Sanitization: The skill performs standard console output of API data without specialized filtering or sanitization of prompt metadata or URLs.

klingai-job-monitoring