stuffed-toy-generator

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The documentation provides examples using curl and npx to interact with the service. These commands execute network requests and run the onekey agent tool, which is the intended interface for the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes text prompts and image URLs supplied by users through the toy_generator_design_draft and toy_generator_task_create functions. This content is sent to external 3D generation providers, creating a surface for potential injection attacks embedded within the source data.
  • Ingestion points: prompt and images parameters in SKILL.md API specifications.
  • Boundary markers: Absent; there are no instructions to the agent to treat these specific fields as untrusted or to wrap them in delimiters.
  • Capability inventory: The skill performs network operations via the OneKey Gateway (agent.deepnlp.org) to submit tasks and retrieve results.
  • Sanitization: No explicit input validation or sanitization rules are documented for the text or URL inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:05 AM
Security Audit — agent-trust-hub — stuffed-toy-generator