skills/cruldra/skills/aliyun-cli/Gen Agent Trust Hub

aliyun-cli

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is entirely composed of shell command templates for the aliyun CLI to manage cloud infrastructure, including ECS instances, OSS storage, and DNS records.
  • [CREDENTIALS_UNSAFE]: The skill provides instructions for configuring AccessKey IDs and Secrets (aliyun configure set). It also includes commands to retrieve SSL private keys (aliyun cas GetUserCertificateDetail), which outputs sensitive credential data to the shell context.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
  • Ingestion points: User-provided inputs are used for command parameters such as --domain-name, --instance-id, and object paths in OSS.
  • Boundary markers: No delimiters or safety instructions are used to distinguish between command structure and user-supplied data.
  • Capability inventory: The skill possesses extensive capabilities including instance deletion (ecs DeleteInstance), DNS record modification (alidns update-domain-record), and file deletion/upload in OSS (oss rm/cp).
  • Sanitization: There is no evidence of input validation or shell escaping provided in the command templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 09:43 AM