Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (PDF files) using libraries like
pypdf,pdfplumber, andpytesseract. This creates a vulnerability surface where instructions embedded in a PDF could attempt to influence the agent's behavior during text extraction or analysis. - Ingestion points: The skill reads external files using
PdfReader,pdfplumber.open(), andconvert_from_path()(inSKILL.md). - Boundary markers: No specific boundary markers or instructions to ignore embedded content are present in the provided code snippets.
- Capability inventory: The skill includes broad capabilities such as file reading, metadata extraction, file writing (
PdfWriter.write,combined_df.to_excel,canvas.save), and OCR processing. - Sanitization: The instructions do not demonstrate sanitization, filtering, or validation of the extracted text before it is returned to the agent context or written to other files.
Audit Metadata