card-twitter
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content to generate design briefs via the
prepare_open_design_brieftool, creating an attack surface where malicious user input could attempt to influence the agent's behavior. - Ingestion points: The user's message is directly treated as the design brief in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt template.
- Capability inventory: The skill allows the agent to author files using local file-editing tools and register artifacts through
register_open_design_artifact. - Sanitization: The instructions do not specify any validation or sanitization of the user-provided brief before it is processed by the design tools.
Audit Metadata