mastra-bedrock

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill references standard AWS credential locations (~/.aws/credentials) and environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY) solely for the purpose of explaining local development configuration. It explicitly instructs developers not to hardcode credentials in the code and relies on the standard @aws-sdk/credential-providers chain to resolve identities securely.
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a standard AI agent pattern where user-supplied prompts are processed to generate responses. This represents the primary intended purpose of the skill.
  • Ingestion points: agent.ts (extracts prompt from the request payload).
  • Boundary markers: None defined in the example; the prompt is passed directly to the model.
  • Capability inventory: The agent is configured with weatherTool in src/mastra/agents/weather-agent.ts.
  • Sanitization: No explicit input sanitization is performed in the provided sample code, as it relies on the underlying LLM's safety guardrails for standard chat interactions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 02:58 PM
Security Audit — agent-trust-hub — mastra-bedrock