Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production hardening (inbound auth, IAM, rate limiting, cold-start tuning).
- Stars
- 3,385
- Version
- v1
- Copies
- 0
Overview
Waxell rates it high risk: 17 findings, highest severity critical.
- Highest severity
- critical
- Findings
- 17
- What ran
- Static analysis
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
Skills in this plugin
We don't republish the plugin's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked 2 days ago
Result
High risk Waxell rates it high risk: 17 findings, highest severity critical.
Checked with static analysis: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. Nothing was run. How the checks work
Findings (17)
critical · 1
- critical
Tells Claude to download a script and pipe it to a shell
skills/agents-debug/references/doctor.md:83 · skill_risk:S1
high · 15
- high
Tells Claude to install unpinned packages (@aws/agentcore)
README.md:58 · skill_risk:S2
- high
Tells Claude to install unpinned packages (bedrock-agentcore, strands-agents, strands-agents-tools)
skills/agents-build/references/browser.md:83 · skill_risk:S2
- high
Tells Claude to install unpinned packages (bedrock-agentcore, nova-act, boto3)
skills/agents-build/references/browser.md:130 · skill_risk:S2
- high
Tells Claude to install unpinned packages (bedrock-agentcore, playwright)
skills/agents-build/references/browser.md:162 · skill_risk:S2
- high
Tells Claude to install unpinned packages (bedrock-agentcore, strands-agents, strands-agents-tools)
skills/agents-build/references/code-interpreter.md:81 · skill_risk:S2
- high
Tells Claude to install unpinned packages (langgraph-checkpoint-aws)
skills/agents-build/references/memory.md:259 · skill_risk:S2
- high
Tells Claude to install unpinned packages (@aws/agentcore)
skills/agents-build/references/payments.md:44 · skill_risk:S2
- high
Tells Claude to install unpinned packages (@aws/agentcore)
skills/agents-debug/references/doctor.md:43 · skill_risk:S2
- high
Tells Claude to install unpinned packages (uv)
skills/agents-debug/references/doctor.md:86 · skill_risk:S2
- high
Tells Claude to install unpinned packages (@aws/agentcore)
skills/agents-get-started/SKILL.md:65 · skill_risk:S2
- high
Tells Claude to install unpinned packages (@aws/agentcore)
skills/agents-pay/SKILL.md:238 · skill_risk:S2
- high
Tells Claude to install unpinned packages (@aws/agentcore)
skills/agents-pay/packages/openclaw/skills/agents-pay/SKILL.md:238 · skill_risk:S2
- high
Tells Claude to install unpinned packages (@aws/agentcore)
skills/agents-pay/references/openclaw-setup.md:39 · skill_risk:S2
- high
Tells Claude to install unpinned packages (@aws/agentcore)
skills/agents-pay/references/operator-guide.md:89 · skill_risk:S2
- high
Tells Claude to install unpinned packages (@aws/agentcore)
skills/agents-pay/references/setup.md:12 · skill_risk:S2
medium · 1
- medium
awsknowledge: connects to an unrecognised server (knowledge-mcp.global.api.aws)
.mcp.json · mcp_risk:M9
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
One version so far: v1 (1.0.0), seen 2026-11-03.
Files
Files
70 files, 796 KB in total. Names only; open them on GitHub.
- .claude-plugin/plugin.json
- .codex-plugin/plugin.json
- .cursor-plugin/plugin.json
- .devin-plugin/plugin.json
- .mcp.json
- README.md
- mcp.json
- plugin.json
- skills/agents-build/SKILL.md
- skills/agents-build/references/browser.md
- skills/agents-build/references/code-interpreter.md
- skills/agents-build/references/integrate.md
- skills/agents-build/references/local-vs-deployed.md
- skills/agents-build/references/memory.md
- skills/agents-build/references/migrate.md
- skills/agents-build/references/multi-agent.md
- skills/agents-build/references/payments.md
- skills/agents-build/references/request-headers.md
- skills/agents-build/references/teardown.md
- skills/agents-build/references/vpc.md
- skills/agents-build/scripts/process_payment_tool.py
- skills/agents-build/scripts/setup_payment_user.py
- skills/agents-connect/SKILL.md
- skills/agents-connect/references/policy.md
- skills/agents-debug/SKILL.md
- skills/agents-debug/references/doctor.md
- skills/agents-deploy/SKILL.md
- skills/agents-deploy/references/versioning.md
- skills/agents-get-started/SKILL.md
- skills/agents-get-started/references/example-support-agent.md
- skills/agents-harden/SKILL.md
- skills/agents-harden/references/limits.md
- skills/agents-optimize/SKILL.md
- skills/agents-optimize/references/cost.md
- skills/agents-optimize/references/evals.md
- skills/agents-optimize/references/observability.md
- skills/agents-pay/.gitignore
- skills/agents-pay/SKILL.md
- skills/agents-pay/packages/openclaw/.gitignore
- skills/agents-pay/packages/openclaw/PUBLISHING.md
- skills/agents-pay/packages/openclaw/README.md
- skills/agents-pay/packages/openclaw/openclaw.plugin.json
- skills/agents-pay/packages/openclaw/package-lock.json
- skills/agents-pay/packages/openclaw/package.json
- skills/agents-pay/packages/openclaw/runtime/agentcore_bridge.py
- skills/agents-pay/packages/openclaw/scripts/stage-skill.mjs
- skills/agents-pay/packages/openclaw/skills/agents-pay/SKILL.md
- skills/agents-pay/packages/openclaw/src/bridge.ts
- skills/agents-pay/packages/openclaw/src/config.ts
- skills/agents-pay/packages/openclaw/src/index.ts
- skills/agents-pay/packages/openclaw/src/payments.ts
- skills/agents-pay/packages/openclaw/src/x402.ts
- skills/agents-pay/packages/openclaw/test/fixtures/v2-security-contract.json
- skills/agents-pay/packages/openclaw/test/security.test.mjs
- skills/agents-pay/packages/openclaw/test/test_agentcore_bridge.py
- skills/agents-pay/packages/openclaw/test/test_setup_openclaw.py
- skills/agents-pay/packages/openclaw/tsconfig.json
- skills/agents-pay/references/openclaw-setup.md
- skills/agents-pay/references/operator-guide.md
- skills/agents-pay/references/security-model.md
- skills/agents-pay/references/setup.md
- skills/agents-pay/references/troubleshooting.md
- skills/agents-pay/requirements.txt
- skills/agents-pay/scripts/agents_pay_admin.py
- skills/agents-pay/scripts/test_portability.py
- skills/agents-pay/scripts/test_resource_resolution.py
- skills/agents-pay/scripts/test_x402_policy.py
- skills/agents-pay/scripts/x402_fetch.py
- skills/agents-pay/scripts/x402_fetch_cli.py
- skills/agents-pay/scripts/x402_policy.py
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
- aws-agents-for-devsecopsawsInvestigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with… High riskEngineeringSecurity3.4k
- setup-devops-agentawsSetup and diagnostics for the AWS DevOps Agent MCP connection. Triggers when aws-devops-agent is missing from .mcp.json, when the… High riskEngineeringAI & agents3.4k
- agents-debugawsUse when your agent or environment is broken: wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to… High riskEngineeringAI & agents3.4k
- aws-transformawsPerforms code upgrades, migrations, and transformations using the AWS Transform (ATX) CLI. Use when upgrading language versions, migrating… High riskEngineeringData & analytics3.4k