content-research-writer

Warn

Audited by Snyk on Aug 14, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). In SKILL.md, Step 3 “Conduct Research” instructs the agent to “Search for relevant information using available tools” and then “Extract key facts, quotes, and statistics” at runtime, meaning outsider-authored web/search content can be ingested for citations.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 14, 2026, 12:08 PM
Issues
1
Security Audit — snyk — content-research-writer