tax-consultant
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill's instructions or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted user data regarding financial income and personal status for its analysis.
- Ingestion points: Data enters the context through user responses to queries about income, investments, and expenses defined in
SKILL.md(Step 1 and Step 2). - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within user-provided data.
- Capability inventory: No capabilities for network operations, file system modifications, or command execution were found in any file.
- Sanitization: There is no evidence of input validation or sanitization, but the lack of dangerous capabilities mitigates the potential impact of an injection.
Audit Metadata