sales-data-extraction-agent
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (Excel files) which constitutes a vulnerability surface for indirect prompt injection. A maliciously crafted Excel file could attempt to influence the agent's behavior during the extraction process.
- Ingestion points: Filesystem watcher monitoring a directory for
.xlsxand.xlsfiles. - Boundary markers: None specified in the instructions.
- Capability inventory: Bulk insertion into PostgreSQL database, fuzzy column mapping, quota calculations, and filesystem monitoring.
- Sanitization: The skill mentions logging, handling currency formatting, and skipping unmatched rows, though it lacks explicit instructions to sanitize against data-based instruction overrides.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata. No scripts, binaries, or platform-specific command injections (such as dynamic context injection) are present.
Audit Metadata