read-source

Warn

Audited by Snyk on Mar 3, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). SKILL.md explicitly allows reading arbitrary web resources (see the "Read from URLs" examples like witan read https://example.com/report.pdf --outline) and describes a pipeline that reads and parses that fetched content to drive parsing and spreadsheet population, so untrusted public web content is fetched and interpreted and can influence downstream actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 07:16 PM