The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized command execution were detected. The skill's behavior is consistent with its stated purpose of managing creator and co-marketing partnerships.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses internal configuration and reference files (e.g., .agents/marketing-context.md) to establish operational constraints. This is standard behavior for providing context to an agent and does not involve exfiltration of sensitive user data or hardcoded credentials.
[INDIRECT_PROMPT_INJECTION]: While the skill involves researching and vetting external creators, it contains instructions for verifying evidence and identity, which provides a natural layer of defense against untrusted external information.

creator-partnerships