esg-screener

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION] (SAFE): The instructions are focused on providing a professional analysis framework for ESG screening. No bypass commands, system prompt extraction, or 'DAN' style role-play injections were detected.
  • [DATA_EXFILTRATION] (SAFE): No access to sensitive file paths (e.g., .ssh, .aws) or network exfiltration patterns are present. The skill suggests using an external toolkit for financial data, which is a standard modular design.
  • [REMOTE_CODE_EXECUTION] (SAFE): There are no scripts or commands that download and execute code from remote sources.
  • [COMMAND_EXECUTION] (SAFE): The skill does not utilize subprocesses, shell commands, or system-level modifications.
  • [INDIRECT_PROMPT_INJECTION] (LOW): While the skill ingests user-specified company lists and likely interacts with external financial data via the referenced toolkit, this is a standard analysis surface. No specific vulnerability was found, though typical LLM boundary safety applies.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM