vfx-text-cursor
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to treat the user's message as a design brief, creating a surface for indirect prompt injection.
- Ingestion point: The user's message content is used as a brief for the
prepare_open_design_brieftool in SKILL.md. - Boundary markers: There are no explicit delimiters or instructions to the agent to treat this data as untrusted or to ignore instructions embedded within the brief.
- Capability inventory: The agent is authorized to use file-editing tools and various MCP tools such as
prepare_open_design_briefandregister_open_design_artifact. - Sanitization: No sanitization or validation of the user-provided brief is mentioned in the instructions.
Audit Metadata