sales-data-extraction-agent
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve monitoring and parsing untrusted Excel files, which represents an attack surface for indirect prompt injection.
- Ingestion points: File monitoring of
.xlsxand.xlssales reports as described in SKILL.md. - Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions within the processed data.
- Capability inventory: The skill specifies capabilities for filesystem monitoring and bulk data insertion into a PostgreSQL database.
- Sanitization: No explicit sanitization or validation of cell content beyond column mapping and currency formatting is mentioned.
- [NO_CODE]: The skill consists of natural language instructions and configuration metadata without any accompanying scripts, executables, or code blocks.
Audit Metadata