general-counsel-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides informational legal frameworks and local analysis tools intended to assist founders in identifying common contract traps and understanding term sheet clauses.
- [COMMAND_EXECUTION]: The skill includes Python scripts (
contract_risk_scanner.py,term_sheet_analyzer.py) designed for local document triage. A review of these scripts confirms they rely solely on Python standard libraries (re,json,argparse,dataclasses) to perform regex-based pattern matching and numerical scoring. They do not execute subprocesses, perform network operations, or access sensitive system paths. - [INDIRECT_PROMPT_INJECTION]: While the skill processes untrusted external data (contracts and term sheets), the processing is handled by local Python scripts rather than direct LLM interpolation. The scripts' outputs are structured and informational, presenting a negligible surface for indirect prompt injection attacks against the agent.
- [DATA_EXPOSURE]: The tools included in the skill operate locally on files provided by the user and do not contain hardcoded credentials or exfiltration logic. The privacy-related checks (e.g., detecting missing Data Processing Agreements) are defensive in nature and serve to improve the user's regulatory compliance.
Audit Metadata