agency-sales-data-extraction-agent
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill monitors and parses external Excel files (.xlsx, .xls), which represents an ingestion point for untrusted content. This creates a surface for indirect prompt injection where malicious instructions hidden in data could influence agent behavior.
- Ingestion points: Filesystem watch directory for sales reports (SKILL.md).
- Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within the Excel data.
- Capability inventory: The agent possesses the capability to read local files, perform bulk inserts into a PostgreSQL database, and emit completion events (SKILL.md).
- Sanitization: While the skill performs fuzzy column mapping and numeric validation, it does not specify methods for sanitizing textual data against prompt injection attacks.
Audit Metadata