The Agent Skills Directory

[SAFE]: The skill contains no executable scripts, binaries, or shell commands. Analysis of the instructions confirms they are limited to providing marketing advice.
[SAFE]: No evidence of prompt injection, obfuscation, or data exfiltration attempts. The skill operates within expected agent behavioral boundaries.
[SAFE]: The skill attempts to read local context files (.agents/product-marketing-context.md) to personalize its responses. While this represents a data ingestion surface, it is a standard practice for agent personalization and does not involve any network operations or sensitive credential access.

community-marketing