Skills
skills/cinience/alicloud-skills/aliyun-rds-supabase/Gen Agent Trust Hub

aliyun-rds-supabase

Fail

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: HIGHDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: Accesses the sensitive Alibaba Cloud credentials file at ~/.alibabacloud/credentials and reads authentication secrets from environment variables ALICLOUD_ACCESS_KEY_ID and ALICLOUD_ACCESS_KEY_SECRET.\n- [COMMAND_EXECUTION]: Supports high-impact administrative operations on cloud resources including DeleteAppInstance, ResetInstancePassword, StopInstance, and RestartInstance as documented in references/api_overview.md.\n- [PROMPT_INJECTION]: Vulnerable to indirect prompt injection via data ingestion from the RDS AI Service.\n
  • Ingestion points: Conversational data retrieved via GetMessages and ChatMessages APIs in references/api_reference.md.\n
  • Boundary markers: Absent. The instructions do not specify delimiters to isolate external conversational content.\n
  • Capability inventory: Significant mutating capabilities including instance deletion, password resets, and security configuration changes across all reference files.\n
  • Sanitization: No evidence of input validation or escaping for the Query parameter or retrieved message content.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Apr 4, 2026, 02:31 PM