competitive-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or unauthorized system behaviors were detected. The skill instructions are focused on professional business analysis and data visualization best practices.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external market data from Excel and CSV files, which creates a potential surface for indirect prompt injection. However, the risk is inherent to the primary function of the skill, and the instructions include data integrity practices that act as functional mitigations.
- Ingestion points: External source files (Excel, CSV) containing competitor metrics.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within source data are provided.
- Capability inventory: The skill uses tools to generate PowerPoint files and charts.
- Sanitization: The instructions prioritize exact data extraction fidelity ("Extract values DIRECTLY") rather than sanitization.
Audit Metadata