ziniao-store

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a vendor-provided command-line tool, ziniao-cli, to manage browser store sessions. It interacts with a local bridge service running at 127.0.0.1:9481 to control browser windows.
  • [PROMPT_INJECTION]: The store open command allows navigation to external URLs, which serves as a potential ingestion point for untrusted data that could influence the agent's behavior. 1. Ingestion points: Content from external websites accessed via the --url parameter in the ziniao-cli store open command (references/ziniao-store-open.md). 2. Boundary markers: None; the instructions do not specify delimiters or safety warnings for processing external web content. 3. Capability inventory: Local browser control and store management functions including listing, opening, and closing stores, and generic command invocation via zclaw (SKILL.md). 4. Sanitization: The skill does not define any methods for sanitizing or validating data retrieved from external pages.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 03:45 PM
Security Audit — agent-trust-hub — ziniao-store