pdf-custom

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes examples that embed plaintext passwords/secret strings (e.g., --password=mypassword, writer.encrypt("userpassword","ownerpassword"), password="secret") and shows passing passwords on the command line, which requires the LLM to handle or reproduce secret values verbatim and is an insecure pattern.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). This skill’s required workflow is a PDF-processing guide that includes runtime text extraction from user-supplied PDFs (e.g., page.extract_text() / pdftotext / OCR pytesseract.image_to_string), so any outsider-authored PDF content could be ingested as free text into the agent’s LLM context.