The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands derived from project-specific files such as Makefile, package.json, Taskfile, and justfile. This execution is the primary function of the skill to ensure project checks pass.
[INDIRECT_PROMPT_INJECTION]: The skill processes project-controlled files to determine its execution path, which presents an attack surface for indirect prompt injection if the files contain malicious commands or instructions.
Ingestion points: CI configuration files, package manager scripts (e.g., check, verify, lint), and build tool configurations (e.g., Makefile, Taskfile.yml, justfile) found within the project repository.
Boundary markers: The instructions do not specify boundary markers or explicit warnings to ignore instructions embedded within the ingested project files.
Capability inventory: The skill has the capability to execute build, test, and linting scripts, as well as interact with configured project tools.
Sanitization: The skill does not perform specific sanitization or validation of the scripts or configuration values extracted from the repository files before execution.

run-checks