The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute standard test commands (e.g., npm test, pytest, go test, cargo test) using the Bash tool. These commands are necessary for the skill's stated purpose of test automation.
[PROMPT_INJECTION]: The skill possesses an indirect injection surface by reading and processing external files from the codebase to identify test configurations.
Ingestion points: The skill reads files like jest.config.*, pyproject.toml, and go.mod in the workspace.
Boundary markers: No specific boundary markers are utilized in the instruction logic.
Capability inventory: The skill uses Bash, Grep, and Read tools.
Sanitization: No explicit sanitization or filtering of file content is performed prior to processing.
[DATA_EXFILTRATION]: No patterns associated with sensitive file access (e.g., .ssh, .env) or unauthorized network exfiltration were found.
[SAFE]: No obfuscation, persistence mechanisms, or privilege escalation patterns were detected in the skill content.

test-runner