best-practices

Warn

Audited by Snyk on Mar 27, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md Phase 1 "Industry Research" Web tool cascade (agent-browser / WebSearch / WebFetch) explicitly requires fetching and reading external public web pages (blogs, community posts, RFCs, official docs) as untrusted input that the agent must interpret to produce the audit, so third‑party content can influence analysis and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 27, 2026, 01:12 AM
Issues
1