researching-codebases

Warn

Audited by Snyk on Mar 14, 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 explicitly includes a web-searcher subagent (agents/web-searcher.md and agent-selection.md) that uses WebFetch to fetch and analyze external web pages (docs, blogs, Stack Overflow/forums) as part of normal workflow, so it ingests untrusted third-party content that can influence agent decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 14, 2026, 04:16 PM
Issues
1