skills/modu-ai/moai-adk/moai-tool-svg/Gen Agent Trust Hub

moai-tool-svg

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill provides legitimate documentation and patterns for SVG development. No malicious code, obfuscation, or persistence mechanisms were identified.\n- [COMMAND_EXECUTION]: The skill instructs the agent to utilize command-line tools such as svgo and npx for SVG optimization and build workflows. This involves standard shell operations for graphic processing within the domain of vector graphics specialist tasks.\n- [PROMPT_INJECTION]: The skill facilitates the processing of SVG files, which could contain instructions intended to influence agent behavior (Indirect Prompt Injection). The risk is mitigated by explicit documentation on using SVGO plugins to sanitize files.\n
  • Ingestion points: Agent reads SVG files from the local workspace or remote sources via WebFetch.\n
  • Boundary markers: Not explicitly defined in the provided templates or instructions.\n
  • Capability inventory: Shell command execution (svgo, npx), file access (Read, Grep, Glob), and network operations (WebFetch).\n
  • Sanitization: The skill provides detailed configuration for svgo to remove scripts, metadata, and editor data, which serves as a security control for processing external vector data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 07:46 AM