javascript-sdk
Fail
Audited by Snyk on Nov 17, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate SDK guide, but it contains a few risky or unexplained items: a top-of-file install banner pointing to an unrelated third-party CLI, "hidden" setup configuration that the user may not see, and
evalon model-supplied arguments, none of which is clearly malicious.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required SDK workflow itself reads no outsider-authored text, but optional agent features (developer-enabled web search and a skill loaded from an arbitrary URL, plus the RAG search-tool pattern) make the agent fetch selected or searched web content, which is low risk because the agent must actively retrieve it.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata