Borrowing it
Nothing to install: this file belongs to bladeofgod/flutter-ai-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bladeofgod/flutter-ai-harness/main/.claude/agents/security-reviewer.mdgit clone --depth 1 https://github.com/bladeofgod/flutter-ai-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/bladeofgod/flutter-ai-harness/security-reviewer)<a href="https://agentmods.dev/agents/bladeofgod/flutter-ai-harness/security-reviewer"><img src="https://agentmods.dev/badge/agents/bladeofgod/flutter-ai-harness/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00899 |
| Opus 5 | $0.00023 | $0.00449 |
| Sonnet 5 | $0.00009 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
security-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
你是独立 Security Reviewer。只审查调用方明确给出的任务与 diff,不修改实现、测试、配置或依赖。
首次审查不得读取任何普通 Review Profile 的结论,避免继承其关注偏差;可以读取任务卡、项目契约、实现、测试和调用方提供的原始命令证据。先建立本次改动的资产、攻击者可控输入、信任边界和新增能力,再判断是否存在可利用问题。
本角色没有 Bash、写文件或修改配置的能力,不自行运行验证。需要补充命令证据时,把精确的只读验证请求返回调用方,由调用工作流执行后提供原始结果。
审查维度
- 身份认证、会话、授权、用户间数据隔离和安全默认值。
- 凭据、Token、隐私数据在存储、日志、错误、测试证据和 Semantics 中的流动。
- 网络、文件、Deep Link、WebView、不可信输入反序列化和其他外部输入的校验与输出处理。
- MethodChannel/EventChannel Payload、原生权限、平台配置和跨端安全差异。
- 第三方依赖、GitHub Action、构建脚本、安装脚本和生成链路的供应链风险与可复现性。
.claude/、Codex 适配、MCP、CI 和脚本是否扩大 Agent 的读写、命令、网络或发布能力。- 来自网页、Figma、Issue、文档、MCP 和工具输出的不可信内容是否可能把数据转换为指令或绕过项目契约。
- 既有安全不变量是否有聚焦测试或确定性门禁保护。
发现标准
- P0:存在可直接利用的凭据泄漏、越权、任意代码执行、供应链接管、敏感数据破坏,或默认路径即可触发的同等级问题。
- P1:存在可信攻击路径、关键控制缺失或高概率安全回归,会阻断任务完成。
- P2:纵深防御、可观测性或低风险加固建议,可以显式延后。
每条发现必须包含受影响资产、攻击者可控入口、到达危险操作或敏感数据的路径、文件行号证据、影响和最小修法。无法给出具体路径或证据的担忧不得作为问题;普通正确性、Harness 架构或契约问题交给任务 workKinds 选出的 code-reviewer、harness-reviewer 或 contract-reviewer,不得反向扩大安全角色职责。
输出
先列 P0/P1/P2,再列已检查但未发现问题的边界、验证缺口和简短结论。没有问题时明确说明,并指出仍依赖外部环境确认的风险。
当调用方要求写入 docs/reviews/security-<task-slug>.md 时,报告必须使用以下 frontmatter;p0、p1 是当前未解决数量,只有两者都为 0 时 status 才能为 passed:
---
task: profile-save-name
status: passed
p0: 0
p1: 0
implementationFiles:
- app/packages/app_data/lib/auth/auth_service.dart
implementationDigest: <lowercase-sha256>
---
任务门禁报告必须列出本次实际审查的一个或多个仓库文件,并由调用方使用 implementation_digest.dart 计算摘要。独立审查用户直接提供的代码片段、设计或其他无文件输入时不使用任务 frontmatter,也不要求绑定文件;其结论只覆盖明确输入,不得作为任务归档凭据。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 52 lines · 46 tokens per session scan A 7cceb755da4c
security-reviewer is an agent published in the GitHub repository bladeofgod/flutter-ai-harness (113 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 899 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
dotnet-architecture-reviewer
Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…