poster-hero
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses a user-provided brief to interact with design tools that return instructions for file modification. This creates a potential trust chain issue where malicious user input could influence the generated instructions.
- Ingestion points: The user's input is directly incorporated into the design brief within
SKILL.md. - Boundary markers: There are no boundary markers or explicit isolation instructions provided to separate the user-supplied brief from the tool's control parameters.
- Capability inventory: The skill utilizes file-editing capabilities and tools such as
register_open_design_artifact. - Sanitization: There is no evidence of sanitization or validation performed on the user's brief before it is passed to the external design server.
Audit Metadata