pdf-processing
Fail
Audited by Snyk on Feb 17, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt includes an explicit example that passes a user-provided PDF password as a literal command-line argument (--password "user_provided_password"), which would require the model to include secret values verbatim and is an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly downloads and processes PDFs from arbitrary URLs (see scripts/download_pdf.py and README/SKILL.md examples using Read(file_path=...) and download_pdf.py), so the agent fetches and then reads untrusted third‑party documents from the open web as part of its workflow, enabling possible indirect prompt injection.
Audit Metadata