verification-before-shipping
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as design plans, briefs, and a state file (
design-state.md), creating a surface for indirect prompt injection. - Ingestion points:
design-state.md, design plans, design briefs. - Boundary markers: Absent.
- Capability inventory: No executable scripts or dangerous tool capabilities are defined or requested in the skill.
- Sanitization: No explicit sanitization of external content is performed.
- [NO_CODE]: The skill consists entirely of Markdown instructions and lacks any executable scripts, shell commands, or dynamic code components.
- [SAFE]: No malicious patterns, such as credential theft, obfuscation, persistence mechanisms, or unauthorized network access, were detected during analysis.
Audit Metadata