web-research-subagent
Warn
Audited by Snyk on Mar 18, 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 explicitly instructs a subagent to "Search the web" and return findings with source URLs (see references/subagent_prompt_template.md and SKILL.md), so it ingests open/public third-party web content (arbitrary URLs) that can influence decisions and thus could enable indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata