custom-agent-definitions

Warn

Audited by Snyk on Apr 21, 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 examples for the "research-agent" and "Read-Only Research Agent" explicitly grant and instruct use of WebSearch/WebFetch (allowed-tools: WebSearch, WebFetch, Read) so the agent will fetch and interpret untrusted public web content as part of its workflow, enabling indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 01:16 AM
Issues
1