tui-upload
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a formatter for user-supplied JSON data, transforming it into specifications for the Pencil MCP drawing environment.
- Ingestion points: User-provided JSON following the 'Input Model' structure in
SKILL.md. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore potential instructions embedded within the input data.
- Capability inventory: The skill's output is intended for consumption by the Pencil MCP, which provides tools for UI element creation.
- Sanitization: The skill does not define methods for sanitizing or validating the input data before interpolation into the design specs.
- [SAFE]: No evidence of malicious code, obfuscation, or unauthorized data access was found in the skill instructions.
Audit Metadata