financial-document-management
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (PDF invoices and image receipts) and uses extracted information to perform file system operations and generate summaries.
- Ingestion points: The skill scans local directories for
.pdf,.jpg, and.pngfiles to extract text content and metadata. - Boundary markers: The instructions do not define explicit boundary markers or provide the agent with guidance to ignore potential malicious instructions embedded within the text of the processed documents.
- Capability inventory: The skill possesses file system manipulation capabilities, including directory creation (
mkdir), file copying (cp), and file moving (mv). It also generates a CSV summary file based on the extracted content. - Sanitization: There is no evidence of sanitization or validation logic to ensure that extracted strings used in filenames or CSV fields do not contain malicious payloads.
Audit Metadata