alipay-merchant-onboarding

Pass

Audited by Gen Agent Trust Hub on May 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is configured to download the official alipay-cli installation script from the vendor's domain at https://opengw.alipay.com/alipaycli/install. This is a legitimate operation from a trusted source to establish the necessary execution environment.
  • [COMMAND_EXECUTION]: The skill executes the downloaded installation script via bash piping and uses the alipay-cli to perform various merchant operations such as status queries and application submissions. These executions are aligned with the primary functionality of the skill.
  • [PROMPT_INJECTION]: The skill ingests untrusted user-provided business descriptions to provide industry category recommendations, which represents a surface for indirect prompt injection. 1. Ingestion points: User descriptions provided during the 'Solution Planning' stage (Step 2). 2. Boundary markers: No specific delimiters are used to wrap the untrusted data. 3. Capability inventory: The skill can execute multiple shell commands via the alipay-cli for account signing and application management. 4. Sanitization: The skill uses jq to parse tool outputs but does not explicitly sanitize the input business descriptions used for semantic matching.
Audit Metadata
Risk Level
SAFE
Analyzed
May 27, 2026, 04:13 AM
Security Audit — agent-trust-hub — alipay-merchant-onboarding