tiangong-kb-edu-search
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The wrapper script uses
npxto download and execute the@tiangong-ai/clipackage from the NPM registry. This is a standard practice for managing the life cycle of the vendor-provided command-line interface tool. - [COMMAND_EXECUTION]: The
edu_search.shscript executes shell commands to interact with the Tiangong AI CLI. It provides a flexible override mechanism via environment variablesTIANGONG_AI_CLIandTIANGONG_AI_CLI_BIN, enabling the entry point to be customized for different execution environments. - [DATA_EXPOSURE]: The skill facilitates access to the local filesystem to load environment variables. It accepts an
env_filepath and also checks for a.envfile in the directory of any providedrequest_file. This mechanism is used to manage authentication credentials and service configurations required for the search operation. - [INDIRECT_PROMPT_INJECTION]: * Ingestion points: Content retrieved from the knowledge base via the
education searchcommand is returned directly to the agent's context. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the resulting output. * Capability inventory: The skill has the capability to execute shell commands and read files from the local filesystem. * Sanitization: There is no evidence of filtering or escaping of the retrieved content before it is processed by the agent.
Audit Metadata