The Agent Skills Directory

[DATA_EXFILTRATION]: The skill interacts with sensitive credential files located at ~/.sealos/kubeconfig and ~/.sealos/auth.json. Access to these files is intrinsic to the skill's purpose of managing resources on the Sealos Cloud platform. The sealos-api.py script uses these credentials to authenticate requests to the Sealos Cloud API.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its requirement to process data from untrusted sources.
Ingestion points: The agent reads application logs via kubectl logs, inspects resource events using kubectl describe, and analyzes user-provided project source code (e.g., Dockerfiles, configuration files) during the build and deployment process.
Boundary markers: There are no explicit instructions for the agent to use boundary markers or specific warnings to ignore instructions embedded within the logs or code it processes.
Capability inventory: The skill possesses significant capabilities, including full kubectl access within the user's namespace, the ability to build and push Docker images using docker buildx, and the ability to perform network requests via curl and sealos-api.py.
Sanitization: The skill does not implement specific sanitization or escaping mechanisms for the external data it retrieves before providing it to the agent for analysis.

use-sealos