quality-screen
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or workflow.
- [PROMPT_INJECTION]: The instructions establish a structured workflow for financial data processing. There are no attempts to bypass safety filters, extract system prompts, or override agent behavioral constraints.
- [COMMAND_EXECUTION]: While the skill mentions the use of shell commands and local tools, these are explicitly restricted to the project's own repository (e.g.,
tools/and~/ai-berkshire/tools/...). This is standard behavior for an agent skill utilizing project-specific utilities. - [DATA_EXFILTRATION]: The skill focuses on collecting public financial data (ROE, FCF, etc.) via web search. It does not attempt to access sensitive local files, environment variables, or hardcoded credentials, nor does it exfiltrate data to unauthorized external domains.
- [EXTERNAL_DOWNLOADS]: No external scripts or packages are downloaded or executed from untrusted sources. All tool references are local to the execution environment.
Audit Metadata