The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute arbitrary shell commands inside Docker containers via the docker compose exec and docker compose run commands.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests content from local files and container outputs that could contain malicious instructions. 1. Ingestion points: The agent reads local docker-compose.yml or compose.yml files and service logs using docker compose logs. 2. Boundary markers: Absent; there are no specific delimiters or instructions provided to the agent to ignore potentially malicious content within the ingested data. 3. Capability inventory: The skill provides the ability to start, stop, and rebuild container stacks, as well as execute commands within running containers. 4. Sanitization: Absent; the skill does not describe any specific validation, filtering, or sanitization of the content retrieved from logs or configuration files.

docker-compose-control