simota-agent-skills
Warn
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads content from a third-party repository hosted on GitHub at https://github.com/simota/agent-skills, which is outside of verified organizations.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a sequence of shell commands, including git clone, git sparse-checkout, and npx skills add, to perform manual installation and directory management.
- [INDIRECT_PROMPT_INJECTION]: The design suite components like frame and pixel are designed to process untrusted data from Figma (via MCP) and image mockups, creating an attack surface for indirect prompt injection.
- Ingestion points: Figma design tokens/context and image mockups.
- Boundary markers: Absent in the provided skill instructions.
- Capability inventory: Access to shell, git, and npx for package management.
- Sanitization: No input sanitization or instruction-filtering is described in the skill logic.
Audit Metadata