The Agent Skills Directory

[PROMPT_INJECTION]: The instructions are focused on community marketing strategy and do not attempt to bypass safety guidelines, extract system prompts, or override agent behavior.
[DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive system file paths were detected in the skill instructions or metadata.
[EXTERNAL_DOWNLOADS]: The skill does not perform any network operations, download external scripts, or reference untrusted remote resources.
[COMMAND_EXECUTION]: There are no shell commands or subprocess execution patterns present in the skill.
[INDIRECT_PROMPT_INJECTION]: The skill instructions advise checking local files such as .agents/product-marketing.md for context. This is a standard pattern for context-sharing between skills and does not introduce significant risk given the skill's lack of dangerous capabilities like network access or file writing.

community-marketing