The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety guidelines were detected. The instructions are focused entirely on product launch strategy.
[DATA_EXFILTRATION]: The skill mentions reading local context files (e.g., .agents/product-marketing.md) to provide better advice. This is a standard feature for context-aware agents and does not involve exfiltration to external domains.
[EXTERNAL_DOWNLOADS]: No remote script downloads or executable binaries are referenced. Links to external sites like coreyhaines.com and Product Hunt are informational and directed at the user.
[COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or system-level operations defined in the instructions.
[REMOTE_CODE_EXECUTION]: No patterns of dynamic code execution or remote script piping (like curl | bash) are present.

launch