contract-gen
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill and its reference files are focused on professional legal drafting. No malicious patterns, obfuscation, or safety bypasses were identified during analysis.
- [COMMAND_EXECUTION]: The script
scripts/generate_contract.jsusesexecSyncto runnpm config get prefix. This is a static, non-interactive command used solely for environment configuration to locate thedocxdependency and does not incorporate user-controlled data. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it interpolates user-provided transaction details into generated documents. (1) Ingestion occurs via contract info inputs in Stage 1; (2) Boundary markers are not explicitly defined in the prompt templates; (3) Capability inventory includes local file writing in Stage 3; (4) Sanitization is provided by a mandatory quality self-check stage and schema validation during the DOCX export process.
- [DATA_EXFILTRATION]: No patterns of data exfiltration were found. The skill's operations are limited to generating and saving document files on the local filesystem.
Audit Metadata