The Agent Skills Directory

[SAFE]: The skill functions as a high-level orchestrator and router within the AFA DTC ecosystem. It does not perform any direct network operations, system command executions, or sensitive file access.
[SAFE]: No hardcoded credentials, API keys, or unauthorized data exfiltration patterns were detected. The skill manages project-specific metadata (e.g., brand-brain files) which is consistent with its stated purpose.
[SAFE]: The skill handles untrusted user input (user_request) but lacks the capabilities (such as shell access or dynamic code evaluation) to be exploited for high-severity indirect prompt injection attacks. It maintains strict output protocols to avoid exposing internal system states.

afa-foundation