mastra-bedrock

Warn

Audited by Snyk on Jul 10, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.95). The required runtime workflow takes an outsider-authored free-text prompt from the HTTP POST /invocations payload (deploy-agentcore.md:124-127), and passes it into agent.generate(prompt, ...), which becomes part of the LLM context (indirect prompt injection risk).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 10, 2026, 02:58 PM
Issues
1
Security Audit — snyk — mastra-bedrock