amazon-bedrock
Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating/porting/converting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching, quota health checks and throttling diagnosis, cost attribution, migrating between Claude model generations, chunking strategies, API selection (Converse vs InvokeModel), and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Coinbase CDP, Stripe Privy, 402 Payment Required, paid endpoint). NOT for custom model training, Rekognition, or Comprehend.
72
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Medium
Suggest reviewing before use
W009: Direct money access capability detected (payment gateways, crypto, banking).
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
The skill explicitly lists a "Payments" AgentCore service that enables agents to pay for APIs/tools via microtransactions and names payment providers (Coinbase CDP, Stripe Privy). This is a specific payment integration (payment gateway / crypto CDP) enabling agents to execute financial transactions.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
In the AgentCore Harness runtime workflow, the LLM ingests caller-provided `messages` via `InvokeHarness(..., messages=[...])` (data-plane) without any requirement to pre-select a specific item, so outsider-authored free text can directly reach the agent at runtime.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The harness documentation shows skills can be fetched from Git at session runtime and injected as trusted agent skills (including scripts), and the skill example uses the git URL "https://github.com/example/skills-repo" which therefore represents a runtime-fetched external source that can control prompts or execute code.
- Repository
- aws/agent-toolkit-for-aws
- Commit
68d9e85
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.