development-plan-ui
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is primarily instructional, focusing on generating markdown documentation and visual layout descriptions. No malicious patterns, exfiltration vectors, or unauthorized code executions were found.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided UI requirements to generate planning documents. While this is an attack surface for instructions embedded in user data, the skill's capabilities are limited to text generation, making the risk negligible.
- Ingestion points: User prompts describing application features, roles, and UI requirements (SKILL.md).
- Boundary markers: The instructions specify that user input should be treated as reference material ('자료로만 취급하며') rather than direct commands.
- Capability inventory: Restricted to markdown text generation; no subprocess calls, network operations, or file-write capabilities were detected in the skill files.
- Sanitization: No explicit input sanitization is defined, but the lack of executable capabilities mitigates this surface.
Audit Metadata