The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard system commands (find) and the Node.js runtime utility (node --check) for file discovery and syntax validation. These are routine operations for a developer tool.
[INDIRECT_PROMPT_INJECTION]: The skill processes project files which could contain malicious instructions. However, the risk is minimal as the skill's instructions focus strictly on correcting syntax errors identified by the Node.js parser rather than executing or interpreting the code logic.
Ingestion points: Project files with the .js extension identified via the find command.
Boundary markers: Absent.
Capability inventory: File system search (find), syntax validation (node --check), and file editing/writing to correct errors.
Sanitization: None; the skill relies on the accuracy and safety of the Node.js syntax checker.

testing-js