The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill's behavior is entirely consistent with its described function as a review tool.
[PROMPT_INJECTION]: The skill uses structured instructional language to guide the AI's behavior but does not contain any instructions to override safety filters, bypass constraints, or ignore system rules.
[DATA_EXPOSURE]: The skill reads project files and documentation to perform analysis. These operations are limited to the context provided by the user for the review and do not involve harvesting sensitive credentials or accessing unauthorized file paths like .ssh or .env.
[COMMAND_EXECUTION]: The skill instructions include using standard platform tools such as Grep and Glob for file inspection. These are used safely for searching within the provided project context.

da-review