short-form-research
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill architecture is modular and role-based, ensuring separation of concerns between data gathering, analysis, and synthesis agents.
- [SAFE]: External references point exclusively to official developer portals and documentation for TikTok, Meta, Google, and LinkedIn.
- [SAFE]: No sensitive system configuration files or credentials are accessed. The skill correctly instructs the use of project-specific context files for audience grounding.
- [SAFE]: The skill implements a Critic Agent that enforces strict quality rubrics, including mandatory source citations and sample-size honesty, which mitigates the risk of misinformation or unverified claims.
- [SAFE]: There are no indicators of prompt injection, persistence mechanisms, or obfuscated payloads in the agent instructions or platform reference documents.
- [SAFE]: The use of the Bash tool is listed in allowed-tools but is not utilized for any dangerous command execution within the provided instructions; its presence is within the scope of intended research operations.
Audit Metadata