aliyun-cli

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting and processing data from external cloud sources, which constitutes an attack surface where maliciously crafted cloud resource metadata or log content could influence agent behavior.
  • Ingestion points: SKILL.md (via aliyun ecs DescribeInstances, aliyun sls GetLogs, and aliyun oss ListObjects).
  • Boundary markers: Not present; instructions do not include delimiters or warnings to ignore embedded instructions in the fetched cloud data.
  • Capability inventory: The skill has significant capabilities including creating superuser database accounts (aliyun rds CreateAccount --AccountType Super), deleting virtual machines (aliyun ecs DeleteInstance), and modifying network security groups.
  • Sanitization: No sanitization or validation of the external data is specified before it is processed or used in subsequent commands.
  • [COMMAND_EXECUTION]: The skill includes bash scripting examples that use command substitution and loops to automate cloud resource management. While standard for administrative tasks, this allows the agent to execute sequences of commands based on the output of previous cloud API calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 11:43 AM