skills/system-desgin/agentds/primer/Gen Agent Trust Hub

primer

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends fetching live design tokens and documentation from an external domain: https://api.agent-ds.oday-bakkour.com/v1/systems/primer/design.md. The documentation also notes that other assets like bundle.zip are available from the same source.
  • [COMMAND_EXECUTION]: Provides instructions to install a 'master skill' using the npx package runner: npx skills add System-Desgin/AgentDS --skill design-systems.
  • [PROMPT_INJECTION]: The DESIGN.md file includes an 'Agent Prompt Guide' designed to influence the agent's behavior and constraints when generating code or UI layouts.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by encouraging the retrieval and processing of external markdown instructions from a remote source (api.agent-ds.oday-bakkour.com).
  • Ingestion points: The curl command in SKILL.md fetches remote content into the agent's context.
  • Boundary markers: No specific delimiters or safety warnings are provided for the remote content.
  • Capability inventory: The skill influences UI generation and code output.
  • Sanitization: No sanitization or validation of the remote content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 02:55 PM
Security Audit — agent-trust-hub — primer