alterlab-vcd-typographer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process external project content—such as brand guidelines, design mockups, and existing project files—to provide context for its work. This creates a surface for indirect prompt injection where instructions embedded in those untrusted design files could influence the agent's behavior. However, the risk is mitigated as the skill primarily produces documentation and does not perform high-privilege system modifications or execute arbitrary code.
Audit Metadata