motion-reference
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data exfiltration were detected. The skill instructions are limited to providing guidance for using specific design reference tools.
- [NO_CODE]: This skill consists purely of instructions in the SKILL.md file and does not include any executable scripts, binaries, or complex configuration files, minimizing the direct attack surface.
- [INDIRECT_PROMPT_INJECTION]: The skill uses tools to ingest animation data and SwiftUI code from a vendor-controlled MCP server (mcp.60fps.design). This is the primary function of the skill and does not pose a threat to the agent's operating environment.
- Ingestion points: Data retrieved via 60fps_get_motion_breakdown and 60fps_get_motion_code tools.
- Boundary markers: None identified in the provided text.
- Capability inventory: The skill does not possess direct shell execution or file-write capabilities; it directs the agent to present findings to the user.
- Sanitization: No explicit sanitization or filtering logic is defined within the instructions.
Audit Metadata