neta-elementum

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions utilize npx -y @talesofai/neta-skills@latest to download and execute code from the npm registry at runtime. This package serves as the primary interface for creating and updating elements within the Neta ecosystem.
  • [COMMAND_EXECUTION]: The skill performs shell command execution through the npx utility to interact with backend services for element management, including creating, updating, and searching for element resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests untrusted user input, such as image prompts and element descriptions, which are then processed by downstream tools and stored in the element's metadata.
  • Ingestion points: User-supplied strings for --prompt and --description arguments in SKILL.md and referenced files.
  • Boundary markers: No specific delimiters or safety instructions are provided to sanitize or isolate these inputs before they are passed to the tools.
  • Capability inventory: The skill calls create_elementum and update_elementum which persist data to a remote resource.
  • Sanitization: The instructions do not include specific sanitization or validation steps for the user-provided content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:52 AM