The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and evaluation data. It does not include any executable code (scripts, binaries), nor does it perform any network operations or system modifications.
[INDIRECT_PROMPT_INJECTION]: The skill contains a directive to read a local context file (.agents/product-marketing-context.md). This is a standard pattern for retrieving user-provided or agent-generated context and does not constitute a malicious injection surface as it is scoped to the local environment and intended for task-relevant data ingestion.
[EXTERNAL_DOWNLOADS]: The instructions mention various well-known services and platforms (e.g., Product Hunt, SparkToro, Hacker News, Navattic) as part of the launch strategy. These references are informative and do not trigger automated downloads or remote code execution.

launch-strategy