current-account-dataset-review
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes dataset files that could contain instructions intended to influence agent behavior.\n
- Ingestion points: Data is read from local files specified via the
--inputflag in the wrapper script.\n - Boundary markers: The wrapper does not define specific delimiters for processed content, relying on the underlying tool logic.\n
- Capability inventory: The CLI tool invoked by the script performs network-based authentication and lifecycle management tasks.\n
- Sanitization: The skill relies on the vendor's CLI for schema validation and data sanitization.\n- [COMMAND_EXECUTION]: The script executes the vendor-owned
tiangong-lcaCLI tool using provided arguments.\n - The execution is performed through a subprocess launcher within the Node.js script.\n
- The script allows for a local CLI directory override, which is a common utility for developers.
Audit Metadata