define
Warn
Audited by Snyk on May 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: 0.80). The skill's research and domain-guidance explicitly require web research and lateral-reading practices (see "when web research is identified as relevant, load tasks/research/sources/SOURCE_WEB.md" in SKILL.md Domain Guidance and the detailed web-research requirements in references/research/README.md), which instruct agents to fetch and evaluate open/public sources and citations that the agent must read and use to form manifest decisions—exposing the agent to untrusted third-party content that could carry indirect prompt-injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata