tax-check
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
pnpm reportandpnpm gainsto run local scripts for tax calculation and report generation. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external financial records. Ingestion points: Reads data from
normalized/capital-gains.json,normalized/w2-data.json,normalized/charitable-donations.json, andreports/tax-ready/form-8949-c.csv. Boundary markers: There are no boundary markers or instructions provided to the agent to treat file content as untrusted data or to ignore embedded instructions. Capability inventory: The skill has command execution capabilities viapnpmand access to sensitive local file paths. Sanitization: There is no evidence of sanitization, escaping, or validation of the content within the financial files before they are interpolated into the agent context.
Audit Metadata