design-guard
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill package is composed entirely of instructional markdown and license documentation. It does not contain any executable scripts, binaries, or automated tool definitions.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes and analyzes external artifacts such as product specifications and mockups. This creates a potential surface for indirect prompt injection; however, since the skill has no defined capabilities for code execution, file writing, or network communication, the threat is categorized as safe.\n
- Ingestion points: Analyzes external design artifacts (specs, mockups, registries) as defined in
SKILL.md.\n - Boundary markers: None explicitly defined in the instructions.\n
- Capability inventory: No executable code, tool access, or script-based capabilities are provided by the skill.\n
- Sanitization: None present in the instructional text.\n- [SAFE]: No malicious patterns, obfuscation, or remote code execution risks were detected in the provided skill files.
Audit Metadata