The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and YAML configuration. It defines frameworks for community management without implementing any executable logic, file system operations, or network communication.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read an external file (.agents/marketing-context.md) as a 'truth file'. While this is a data ingestion point, the skill lacks any dangerous capabilities (tools, scripts, or network access) that could be exploited via malicious content in that file, resulting in no actual security risk.

community-programs