The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script scripts/generate_bobo.py to generate the Kubernetes YAML manifests. This is a standard functional component of the skill's design.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill references a container image located at quay.io/cooloo9871/bobo:latest. This image is hosted on a well-known container registry and belongs to the skill's author, posing no unexpected security risk.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data (image name and replica count) to populate a configuration template.
Ingestion points: Parameters are passed from the user's prompt to the generate_bobo.py script via SKILL.md instructions.
Boundary markers: Not present; the skill relies on the agent to correctly pass the requested values.
Capability inventory: The associated script only performs string formatting and prints to the console; it lacks system-level capabilities such as file writing, network access, or command execution beyond the generation itself.
Sanitization: Input is interpolated directly into the template string without specific sanitization, but given the lack of dangerous capabilities, the risk is negligible.

bobo-skill