superior-ui-audit
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted product source code and design documentation to generate audit reports and change plans. A malicious actor could embed instructions within these source files to manipulate the agent's output, particularly the shell commands suggested for validation.
- Ingestion points: Product source code and design/brand documentation (SKILL.md).
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill generates a change plan template that includes a 'Repository checks' section for executing shell commands (references/change-plan.md).
- Sanitization: There is no evidence of sanitization or validation of the content extracted from external sources before it is used to populate the change plan.
Audit Metadata