wire-up-interactions
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [PROMPT_INJECTION]: No override or bypass markers were detected. The skill contains explicit instructions to maintain safety boundaries and only claim actions that were actually completed.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file paths or network operations were found. The skill operates locally within the user's provided design context.
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: No external packages or remote scripts are downloaded or executed. The skill is purely instructional markdown.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (Figma design context), which creates a potential injection surface.
- Ingestion points: Figma metadata, frame names, layer names, component states, variables, and comment threads (SKILL.md).
- Boundary markers: Absent; there are no specific delimiters to isolate external content.
- Capability inventory: None; the skill lacks any capabilities for command execution, file system access, or network transmission.
- Sanitization: Absent; the instructions do not specify validation or sanitization for design context data.
Audit Metadata