Fail
Audited by Snyk on Feb 15, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The prompt includes examples that hardcode or pass passwords on the command line (e.g., writer.encrypt("userpassword","ownerpassword") and qpdf --password=mypassword), which instructs embedding secret values verbatim and thus poses an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly reads and processes arbitrary user-supplied PDF files (e.g., scripts like extract_form_field_info.py, convert_pdf_to_images.py, fill_pdf_form_with_annotations.py and fill_fillable_fields.py open and parse input PDFs), so the agent ingests untrusted third-party content that could contain embedded instructions.
Audit Metadata