alicloud-network-esa

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes data from external Alibaba Cloud APIs that could contain malicious instructions.
  • Ingestion points: The skill retrieves dynamic data such as site names, plan types, and DNS record values through scripts like scripts/list_sites.py and scripts/list_dns_records.py.
  • Boundary markers: The processing logic lacks explicit delimiters or instructional constraints that would prevent the agent from inadvertently following commands embedded in the retrieved metadata.
  • Capability inventory: The skill has significant operational reach, including the ability to delete sites (DeleteSite), modify DNS records (UpdateRecord), and deploy or execute custom code on edge nodes via Edge Routine (CreateRoutine).
  • Sanitization: There is no evident validation or sanitization of the data retrieved from the cloud environment before it is used in the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 03:29 AM