budget-variance-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted financial data provided by the user in the form of tables.
- Ingestion points: Financial actuals and budget data provided in user prompts as described in the description and workflow.
- Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded commands within the financial data.
- Capability inventory: None. The skill does not use tools, shell commands, or network operations.
- Sanitization: No sanitization or validation of input data is present.
- [NO_CODE]: The skill consists entirely of Markdown instructions and does not include any scripts, configuration files, or external packages, significantly limiting the potential attack surface.
Audit Metadata