research-patterns

Warn

Audited by Snyk on Mar 31, 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). This skill's SKILL.md explicitly requires performing external web research and WebFetch/WebSearch of public sources (see "External Web Research" and examples like "WebFetch: Martin Fowler, microservices.io, AWS architecture blog" and the "Top sources fetched (5+ WebFetch calls)" quality gate), so the agent will ingest and act on untrusted third-party content that can influence downstream decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 31, 2026, 12:11 PM
Issues
1