write-longform

Warn

Audited by Snyk on Jul 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via the research agent’s runtime WebSearch/WebFetch step (public web pages/articles scraped from URLs), whose readable page text is then assembled into the Evidence Ledger and passed downstream into outline/draft/critic.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 4, 2026, 10:16 PM
Issues
1
Security Audit — snyk — write-longform