budget-builder
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, prompt injection attempts, or unauthorized access behaviors were detected in the skill instructions.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any scripts, dependencies, or executable binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface for user financial information, though it lacks the capabilities to exploit such data.
- Ingestion points: Monthly income, fixed expenses, and variable spending data collected in Step 1 and the provided template.
- Boundary markers: The template uses clear headers and placeholders, but does not implement specific delimiters to isolate user input from instructions.
- Capability inventory: None. The skill uses no external tools, shell commands, or network operations.
- Sanitization: No explicit input sanitization is performed, but risks are mitigated by the absence of executable capabilities.
Audit Metadata