The Agent Skills Directory

[DATA_EXPOSURE]: The skill instructs the agent to check for and read local context files, specifically .agents/product-marketing.md or similar filenames. This is a legitimate mechanism for the agent to acquire project-specific marketing knowledge and does not involve accessing sensitive system credentials or private user data.
[PROMPT_INJECTION]: The instructions were analyzed for attempts to override safety guardrails or bypass system prompts. No such patterns were found. The language used is purely instructional regarding marketing and design best practices.
[REMOTE_CODE_EXECUTION]: There are no commands or instructions that trigger external downloads, package installations, or the execution of remote scripts.
[COMMAND_EXECUTION]: The skill does not contain any shell commands, subprocess invocations, or instructions for the agent to execute code on the host system.

popups