research-finance
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill consists of deterministic Python scripts for financial calculations (budgeting, burn rate, runway) that do not use LLM calls or external network requests.
- [DATA_EXFILTRATION]: The skill does not access sensitive system files or credentials. All data processing is performed on user-provided JSON files and local configuration stored in standard app-specific directories.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns were found. The skill is documented as 'stdlib-only' and manual inspection of the source code confirms it does not use package managers, download external scripts, or utilize unsafe execution functions like eval() or exec().
- [PROMPT_INJECTION]: The instructions and reference materials are professional and focus on financial modeling standards (IAS 38, ASC 730). There are no attempts to override agent behavior, bypass safety filters, or extract system prompts.
Audit Metadata