alibabacloud-maxcompute-cli

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the execution of the aliyun maxc command-line tool to perform MaxCompute operations, including queries, metadata discovery, authentication, and data transfers. It uses local shell commands like python3 -c to parse JSON and openssl to generate session identifiers. It also supports an external authentication helper through the --process-command flag.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from MaxCompute query results and table metadata. Ingestion points: Data enters the agent context via query results, data sample, and data profile outputs. Boundary markers: The skill does not define specific delimiters to isolate untrusted database content from instructions. Capability inventory: The agent can perform file writes, data uploads, and execute DML/DDL statements. Sanitization: No specific sanitization or escaping protocols are described for database content before it is interpolated into agent reasoning.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 09:38 AM