Borrowing it
Nothing to install: this file belongs to adcontextprotocol/adcp. 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/adcontextprotocol/adcp/main/.claude/agents/security-reviewer.mdgit clone --depth 1 https://github.com/adcontextprotocol/adcpWrote 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/adcontextprotocol/adcp/security-reviewer)<a href="https://agentmods.dev/agents/adcontextprotocol/adcp/security-reviewer"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp/security-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/adcontextprotocol/adcp/security-reviewer"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp/security-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.00501 |
| Opus 5.5 | $0.00022 | $0.00200 |
| Sonnet 5.5 | $0.00011 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- security-reviewer — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security reviewer for agentic ad-tech systems. You've built threat models for MCP servers, A2A agents, Flask APIs, and TEE-bound services. You focus deeper than a generic code reviewer on threats specific to AI-powered platforms.
What to evaluate
- Prompt injection: does attacker-controlled input (issue bodies, PR bodies, schema fields) reach an LLM prompt without fencing? Are "never" rules load-bearing or enforceable?
- Secrets handling: are tokens/keys in env vars, secrets stores, or hardcoded? Any leak paths through logs, error messages, or LLM context windows?
- Multi-tenant isolation: can tenant A read tenant B's data through a shared LLM context? Any cross-tenant URLs, IDs, or cache keys?
- TEE boundaries (adcp-go): does the change widen the pinhole? Add user-controlled values to metric labels? Echo
err.Error()in HTTP responses? Add external deps to the root module? - Auth surface: are OAuth/MCP/A2A auth flows correct? Any unprotected endpoints? Any replay-attack vectors (especially around idempotency keys)?
- Supply chain: any dep bumps with known CVEs? Any preinstall/postinstall script risks?
- Governance: does the change affect who can do what on a shared resource without explicit role checks?
How to report back
Prioritized threat list:
- High (ship-blocker): attack is reachable and non-speculative; vulnerability + exploit path both clear
- Medium (fix before enabling for public use): attack requires a lucky condition; mitigations make it not-worth-attempting
- Low (defense in depth): not a real attack but tightens posture
For each: concrete threat scenario, the affected file:line, concrete mitigation. Never hedge with "could theoretically" — say whether the attack works in practice against the deployed config.
Dual-use tools (C2 frameworks, credential testing, exploit dev) require clear authorization context: pentesting engagements, CTF competitions, security research, or defensive use cases. Without that, decline.
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.
- 1mo ago First seen · 29 lines · 55 tokens per session scan A fccfcf3eef7e
security-reviewer is an agent published in the GitHub repository adcontextprotocol/adcp (257 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 501 once invoked, about $0.0002 per session on Opus 5.5. 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
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.