Skip to content

davepoon/buildwithclaude / plugins/production-fast-api-template/skills/production-fast-api-template

production-fast-api-template

Unverified

Structure and execution rules for a unified, production-ready backend combining domain-oriented FastAPI, Retrieval-Augmented Generation (RAG) and Agentic AI in one codebase on AWS ECS Fargate. Use when scaffolding a new backend; adding a module, API domain, RAG component, agent, tool, workflow, LLM/provider integration or test; deciding where a file belongs; writing async/sync routes, services or clients; offloading blocking or CPU-heavy work (thread pools, process pools, AWS Lambda); designing background jobs, queues (SQS, Celery), workers and scaling; or writing Pydantic schemas, settings (pydantic-settings), serialization, structured LLM outputs, citation validation, agent plans or tool-call arguments; or writing FastAPI dependencies (request validation, auth, access scopes, chaining), REST paths, response models, OpenAPI docs, error responses, database naming and SQL queries, migrations, API tests (async client, dependency overrides) or lint/format setup (ruff); or adding content-safety guardrails (input/output checks, PII, prompt injection, toxicity, Bedrock Guardrails, AgentCore Policy/Gateway Cedar policies, Guardrails AI validators), fail-closed handling and guardrail evaluation; or evaluating RAG, retrieval stages, structured outputs, citations, agents, multi-agent workflows or conversations (DeepEval, Ragas, LLM-as-judge, G-Eval, golden datasets, regression tiers, thresholds, judge calibration); or securing the API (authentication, JWT/JWKS, OAuth 2.0/OIDC, RBAC/ABAC, BOLA/BFLA, tenant isolation, input/upload/SSRF validation, security headers, CORS, CSRF, rate limiting, audit logging, ECS/IAM/secrets hardening, CI security scanning, security tests) or LLM/agent security (OWASP LLM Top 10, OWASP Agentic Top 10, prompt injection, tool authorization, human approval, excessive agency).

Security report

Unverified

Static analysis of one exact version. It reduces risk and shows evidence; it does not certify that a skill is safe.

Commit
3c9a725a1c4e41f80e224e1d4e5940f402d9bbda
Content hash
3ed692f78c431d77c59e0de2e249c6a27519ad7e5cd7659cd5b1193c87b0ad65
Scanned
2026-11-17
Scanner version
skillxone-scan-1.0.0
Policy version
0.1-draft
Decision
2 open medium findings to review.
Verification expires
Not applicable

Findings (2 medium, 2 low)

  • mediumNET-CLOUD-METADATAAPI_SECURITY.md:441

    The cloud instance metadata service is contacted. On a cloud machine it hands out credentials. Severity lowered from high because it appears in prose rather than code.

    - Block private, loopback, link-local, multicast, unique-local and reserved ranges (IPv4 and IPv6, including IPv4-mapped IPv6), plus **cloud metadata endpoints**: `169.254.169.254`, `fd00:ec2::254` (EC2 IMDS) and `169.254.170.2` (ECS task …

    Suggested fix: Remove access to the metadata service.

    Report as false positive

  • mediumPI-JAILBREAK-PERSONAGUARDRAILS.md:417

    The text uses language typical of jailbreak prompts.

    | Check fires (denied / suppressed) | **No.** Regenerating until the output passes is prompt-level jailbreaking of our own guardrail. | Block per §4 |

    Suggested fix: Remove the jailbreak framing.

    Report as false positive

  • lowPI-REVEAL-PROMPTAGENT_SECURITY.md:36

    The text asks the agent to disclose its system prompt or hidden instructions. Severity lowered from high because the surrounding text warns against it.

    | 3 | Authorization is decided in code (`auth/`, `rag/security/`, `agents/security/`, `execution/`), never in a prompt. "Never reveal X" in a system prompt is not access control. | 🟢 |

    Suggested fix: Remove the request. A skill has no need to read or reveal the system prompt.

    Report as false positive

  • lowPI-IGNORE-INSTRUCTIONSAGENT_SECURITY.md:328

    The text tells the agent to ignore or override its existing instructions, a common prompt-injection pattern. Severity lowered from high because it appears in a quotation.

    | Prompt and content | Direct "ignore previous instructions"; indirect injection in HTML, PDF, email, ticket and repository fixtures; hidden Unicode, Markdown, comments, encodings, multilingual and image text; long-context distraction; rol…

    Suggested fix: Remove the instruction. A skill should add guidance for its task, not cancel the instructions the agent already follows.

    Report as false positive

Checks run

  • prompt-injection
  • dangerous-commands
  • credentials
  • network
  • file-access
  • integrity

Checks skipped

  • dependencies: No dependency manifest in the skill directory.
  • gitleaks: gitleaks is not installed on this host.
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall