design-audit
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data which serves as a potential surface for indirect prompt injection from untrusted source code or configuration files.
- Ingestion points: The skill reads project source code and local files such as
.design-context.mdand.design-critique/ignore.md(SKILL.md). - Boundary markers: There are no specific delimiters or instructions to ignore embedded commands within the audited files.
- Capability inventory: The skill's instructions are limited to report generation; it lacks functionality for file writes, network communication, or shell command execution.
- Sanitization: No content sanitization or escaping is performed on the audited data before inclusion in the report output.
Audit Metadata