deep-research

Warn

Audited by Snyk on May 1, 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). The skill's required RETRIEVE workflow (reference/methodology.md Phase 3 and SKILL.md) explicitly performs web searches, page extraction and scraping via search-cli/WebSearch (e.g., search "URL" -m extract / search "URL" -m scrape), spawns agents to read PDFs/web pages, and persists quotes/URLs into evidence.jsonl—meaning the agent will fetch and interpret arbitrary public web content that can materially change its next actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 1, 2026, 09:17 PM
Issues
1