Sales Data Extraction Agent
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse external Excel files (.xlsx, .xls) from monitored directories, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: Files detected in the watch directory are processed to extract metrics (SKILL.md).
- Boundary markers: The instructions do not define boundary markers or clear delimiters to help the agent distinguish between data to be extracted and potential instructions embedded within the spreadsheet cells.
- Capability inventory: The skill has the capability to perform bulk inserts into a PostgreSQL database and emit completion events for downstream agents.
- Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from cells before it is processed or stored, making the agent susceptible to obedience of instructions hidden within the sales data.
Audit Metadata