The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the bash tool to execute docker build, docker run, make, and pytest commands. The docker run command is configured with a host volume mount (--volume "$(pwd):/tmp/lint"), allowing the container to interact with the project's directory.\n- [PROMPT_INJECTION]: The skill includes behavioral instructions such as "Do not stop to ask mid-loop," which increases the agent's autonomy. It also creates a surface for indirect prompt injection by processing external project files like descriptors and Dockerfiles.\n
Ingestion points: Local repository files including linters/*/Dockerfile and descriptors.\n
Boundary markers: None identified in the prompt instructions.\n
Capability inventory: Access to bash, docker, make, Read, Write, and Edit tools.\n
Sanitization: No explicit sanitization of repository-provided data before use in commands.

test