web-scraping
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a user-invoked workflow where outsider-provided arbitrary URLs/content can be fetched and converted to Markdown/HTML via
mq-crawl(andmq --allow-net/http()), so the LLM can ingest free text from non-trusted authorship at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata