financial-projections
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill uses instructional text to guide an AI agent through a financial evaluation process.- [DATA_EXFILTRATION]: The skill collects founder financial data (savings, expenses) which is sensitive, but it is used solely for the intended purpose of the analysis within the agent's context. No instructions to send this data to external servers were found.- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting data from external web searches and user-provided descriptions.
- Ingestion points: User-provided business context (Step 0) and competitor/market data from autonomous web research (Step 1).
- Boundary markers: None; the skill does not specify delimiters for external content.
- Capability inventory: The skill's capabilities are restricted to research tool usage and producing a structured markdown report. It lacks the ability to execute commands, write files, or perform network exfiltration.
- Sanitization: No sanitization or validation methods for external inputs are defined in the instructions.
Audit Metadata