lifecyclemodel-recursive-orchestrator
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The Node.js script located at scripts/run-lifecyclemodel-recursive-orchestrator.mjs serves as a wrapper for the tiangong CLI. It processes user arguments and executes shell commands to perform planning, execution, and publishing tasks associated with LCA model orchestration. This functionality is consistent with the skill's stated purpose.
- [PROMPT_INJECTION]: The skill ingests external data from JSON request files, such as assets/example-request.json, which represents a surface for indirect prompt injection. Maliciously crafted content within these files could potentially influence agent behavior during the orchestration process.
- Ingestion points: Structured data is read from local files via the --request argument in scripts/run-lifecyclemodel-recursive-orchestrator.mjs.
- Boundary markers: The provided documentation and scripts do not specify boundary markers or instructions to isolate the data from the agent's control logic.
- Capability inventory: The skill has command execution capabilities through its integrated CLI wrapper.
- Sanitization: The script performs basic normalization of arguments, but comprehensive validation and sanitization of the JSON content are delegated to the underlying CLI tool.
Audit Metadata