The Agent Skills Directory

[DATA_EXPOSURE]: The skill instructs the agent to look for and read local context files such as .agents/product-marketing.md or .claude/product-marketing.md before prompting the user for information. This is a standard and safe design pattern for context-aware agents to avoid repetitive questioning and does not target sensitive system credentials or private keys.
[PROMPT_INJECTION]: The instructions are focused on providing marketing strategy expertise. There are no attempts to override system prompts, bypass safety filters, or use adversarial role-play techniques.
[EXTERNAL_DOWNLOADS]: The skill references external platforms and tools like Product Hunt, Introw, and Navattic in a descriptive marketing context. It does not contain any commands to download, install, or execute third-party software or scripts.
[COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic code execution patterns are present in the skill instructions or supporting files.

launch