The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes a local Python script python .codestable/tools/search-yaml.py to search for existing documentation within the project. This script is used for duplicate detection and updating existing files as part of the intended workflow.- [DATA_EXFILTRATION]: There are no network requests or external data transfers. The skill's operations are confined to reading and writing files within the project's local .codestable/ directory.- [PROMPT_INJECTION]: The instructions provide a clear, step-by-step workflow for data collection and do not include attempts to override system prompts or bypass safety guardrails.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by reading existing markdown documents from the project to perform updates (Phase 1.5). While this creates a potential surface for indirect injection, the risk is minimized by the mandatory Phase 3 review step and the limited scope of the skill's capabilities.

cs-learn