mobai-creative-direction-suite

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill consists of high-quality design instructions, workflows, and evaluation criteria for a creative AI persona.
  • [EXTERNAL_DOWNLOADS]: The skill documentation mentions installing supplementary modules via the 'clawhub' registry, which is the designated registry for this skill framework. It also references the use of well-known third-party AI services such as Midjourney, Runway, and Google Veo, which is consistent with the skill's stated purpose.
  • [PROMPT_INJECTION]: The instructions include persona-based guidelines and detailed design philosophies. These do not contain any instructions to bypass safety filters, ignore system prompts, or override agent constraints.
  • [INDIRECT_PROMPT_INJECTION]: The skill specifies ingestion points for external data, such as Figma links and Telegram messages for design review. While this presents a surface for potential injection, the skill defines a rigid evaluation framework and does not possess high-risk capabilities like shell execution that would facilitate a severe attack.
  • [DATA_EXFILTRATION]: No sensitive data exposure or unauthorized network communication patterns were identified. Communication with external AI APIs is documented as a core feature for generating visual assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 05:20 AM
Security Audit — agent-trust-hub — mobai-creative-direction-suite