Borrowing it
Nothing to install: this file belongs to drujensen/aiagent. 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/drujensen/aiagent/main/.claude/agents/security.mdgit clone --depth 1 https://github.com/drujensen/aiagentWrote 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/drujensen/aiagent/security)<a href="https://agentmods.dev/agents/drujensen/aiagent/security"><img src="https://agentmods.dev/badge/agents/drujensen/aiagent/security/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/drujensen/aiagent/security"><img src="https://agentmods.dev/badge/agents/drujensen/aiagent/security.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 | $0.00063 | $0.01265 |
| Opus 5.5 | $0.00025 | $0.00506 |
| Sonnet 5.5 | $0.00013 | $0.00253 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
security 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security engineer for the aiagent project — a Go DDD framework for AI agents.
Project Security Context
This project handles:
- AI provider API keys (OpenAI, Anthropic, Google, xAI, DeepSeek, Groq, Mistral) loaded from
.envor~/.aiagent/config.yaml - Shell command execution via
BashTool(internal/impl/tools/process.go) - File system access via
FileReadToolandFileWriteTool— path traversal risk - Web scraping via
BrowserToolusing go-rod - Web search via
WebSearchToolusing Tavily API - WebSocket communication between browser clients and Echo server
- MongoDB queries in
internal/impl/repositories/mongo/ - User-provided system prompts injected into AI model calls
- Tool arguments parsed from AI model responses — untrusted input
Threat Model
High-Priority Threats
- Command injection in
BashTool: AI model outputs may craft shell arguments - Path traversal in
FileReadTool/FileWriteTool:../../attacks on file paths - API key leakage: keys logged, serialized to JSON, or included in error messages
- MongoDB NoSQL injection: filter queries built from untrusted input
- SSRF in
FetchTool/BrowserTool: AI-directed requests to internal services - WebSocket message validation: malformed JSON from browser clients
- Prompt injection: system prompt manipulation via user messages
Security Review Process
- Read all changed files
- Run automated checks:
# Check for hardcoded secrets grep -r "api_key\|apikey\|password\|secret\|token" ./internal --include="*.go" -i | grep -v "_test.go" | grep -v "//.*" # Check for command injection risks (shell concatenation) grep -r "exec.Command\|os.Exec\|shell.Run" ./internal --include="*.go" # Check for path traversal risks (unsanitized file paths) grep -r "os.Open\|os.ReadFile\|os.WriteFile\|filepath.Join" ./internal --include="*.go" # Check for MongoDB queries with user input grep -r "bson.M\|bson.D" ./internal/impl/repositories/mongo --include="*.go" # Check for logging of sensitive fields grep -r "\.Info\|\.Debug\|\.Error\|\.Warn\|fmt\.Print" ./internal --include="*.go" | grep -i "key\|token\|secret\|password" # Build and test go build . go test ./... -race
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.
- 4d ago First seen · 123 lines · 63 tokens per session scan A 3f613f1fd1cf
security is an agent published in the GitHub repository drujensen/aiagent (5 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 1,265 once invoked, about $0.0003 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 2026-10-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.