wps-pdf-extract
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing external documents.
- Ingestion points: The
PDFExtractorclass inSKILL.mdreads and parses content from user-provided PDF files usingfitzandpdfplumberlibraries. - Boundary markers: None. There are no instructions or markers to distinguish between the skill's operational logic and the untrusted content extracted from the PDFs.
- Capability inventory: The skill's frontmatter configuration allows access to powerful tools including
Bash,Write, andEdit. Additionally, the internal Python scripts perform file system operations such as directory creation (os.makedirs) and file writing (pix.save,doc.save,wb.save). - Sanitization: None. Extracted text and data are handled directly without filtering or sanitization, meaning any instructions embedded in a processed PDF could be interpreted and acted upon by the agent.
Audit Metadata