tech-research
Warn
Audited by Snyk on Apr 16, 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). This skill explicitly drives browser-based Grok queries against X/Twitter (user-generated posts) and uses WebSearch/WebFetch and DeepWiki (public GitHub repos) as required sources in SKILL.md and references/subagent_templates.md — the agent reads and synthesizes those untrusted, third‑party contents to make recommendations and next-action decisions, enabling indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata