alibabacloud-kafka-capacity-assessment

Fail

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and execute a setup script from aliyuncli.alicdn.com. This domain belongs to the official Alibaba Cloud content delivery network. Since the skill is authored by aliyun, this is classified as an intended installation of vendor management tools from a recognized source.
  • [COMMAND_EXECUTION]: The skill relies on aliyun CLI and shell commands to retrieve metadata and performance metrics. The instructions explicitly limit the agent to read-only operations and include strict prohibitions against echoing or printing credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external APIs which is then processed to generate reports, representing an indirect injection surface.
  • Ingestion points: The skill reads responses from the aliyun alikafka get-instance-list and aliyun cms describe-metric-list API calls as defined in the core workflow of SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore potential commands within the data are used when processing the API output.
  • Capability inventory: The skill environment includes shell command execution through the aliyun CLI and mentioned potential for Python or Terraform execution.
  • Sanitization: There is no provided logic for validating or sanitizing the data returned from the cloud APIs before it is incorporated into the agent's context.
Recommendations
  • HIGH: Downloads and executes remote code from: https://aliyuncli.alicdn.com/setup.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 18, 2026, 07:41 AM