planning

Warn

Audited by Snyk on Apr 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: 0.90). The skill's Discovery phase and its discovery template explicitly require "Agent D: External Research" using web_search/WebFetch/library docs (references/discovery-template.md and Phase 1: Discovery in SKILL.md), which instructs the agent to fetch and read public third-party docs/community patterns/URLs and incorporate those findings into discovery.md and the approach/risk decisions — meeting the criteria for consuming untrusted web content that can change tool use and next actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 14, 2026, 02:26 PM
Issues
1