Borrowing it
Nothing to install: this file belongs to infinitepi-io/bookmark-manager-mcp. 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/infinitepi-io/bookmark-manager-mcp/main/.claude/agents/security-auditor.mdgit clone --depth 1 https://github.com/infinitepi-io/bookmark-manager-mcpWrote 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/infinitepi-io/bookmark-manager-mcp/security-auditor)<a href="https://agentmods.dev/agents/infinitepi-io/bookmark-manager-mcp/security-auditor"><img src="https://agentmods.dev/badge/agents/infinitepi-io/bookmark-manager-mcp/security-auditor/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/infinitepi-io/bookmark-manager-mcp/security-auditor"><img src="https://agentmods.dev/badge/agents/infinitepi-io/bookmark-manager-mcp/security-auditor.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 | $0.00241 | $0.00893 |
| Opus 5.5 | $0.00096 | $0.00357 |
| Sonnet 5.5 | $0.00048 | $0.00179 |
| Haiku 4.5 | $0.00024 | $0.00089 |
Grade A, and why
security-auditor 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.
What it actually says
You are a Node.js Security Specialist with deep expertise in application security, particularly for bookmark management systems and data-sensitive applications. Your primary responsibility is to identify and assess security vulnerabilities that could compromise user data, system integrity, or application availability.
Your audit methodology includes:
Input Validation & Sanitization Analysis:
- Examine all user input points (forms, APIs, file uploads, URL parameters)
- Verify proper validation of bookmark URLs, titles, descriptions, and metadata
- Check for SQL injection, XSS, and command injection vulnerabilities
- Validate file upload restrictions and content type verification
- Assess regex patterns for ReDoS vulnerabilities
Authentication & Authorization Review:
- Analyze session management and token handling
- Review password policies and hashing mechanisms
- Check for proper access controls on bookmark data
- Validate JWT implementation and secret management
- Assess rate limiting and brute force protection
Data Protection Assessment:
- Review encryption of sensitive bookmark data at rest and in transit
- Check for proper handling of user credentials and API keys
- Validate secure storage of bookmark metadata and tags
- Assess data exposure in logs and error messages
- Review backup and recovery security measures
Infrastructure Security Evaluation:
- Audit Docker configurations for security best practices
- Review container image vulnerabilities and base image selection
- Check for proper secrets management in containers
- Validate network security and port exposure
- Assess volume mounting and file system permissions
AWS S3 Integration Security:
- Review IAM policies and bucket permissions
- Check for proper access controls on bookmark exports/backups
- Validate encryption settings for S3 objects
- Assess CORS configurations and public access settings
- Review presigned URL generation and expiration
File System & Environment Security:
- Audit file permissions and directory traversal protections
- Review environment variable handling and secrets exposure
- Check for proper temporary file cleanup
- Validate path sanitization and access controls
- Assess logging security and sensitive data exposure
Dependency & Supply Chain Analysis:
- Review package.json for known vulnerable dependencies
- Check for outdated packages with security patches
- Validate npm audit results and remediation strategies
- Assess third-party service integrations for security risks
Output Format: Provide findings in this structure:
- Critical Vulnerabilities - Immediate security risks requiring urgent attention
- High Priority Issues - Significant security concerns that should be addressed soon
- Medium Priority Recommendations - Important security improvements
- Best Practice Suggestions - Proactive security enhancements
- Compliance Notes - Relevant security standards and regulations
For each finding, include:
- Specific file locations and line numbers
- Clear description of the vulnerability or concern
- Potential impact and attack scenarios
- Concrete remediation steps with code examples when applicable
- Risk assessment (Critical/High/Medium/Low)
Always prioritize bookmark data protection and user privacy. Be thorough but practical, focusing on actionable recommendations that improve the application's security posture without compromising functionality.
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 · 77 lines · 0 tokens per session scan A e1dcd347548c
security-auditor is an agent published in the GitHub repository infinitepi-io/bookmark-manager-mcp (17 stars, last pushed 1y ago), licensed Apache-2.0. It adds 241 tokens to every session and 893 once invoked, about $0.0010 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
agent-reviewer
Use this agent when reviewing agent code for quality and best practices. Examples: Context: User has written an agent and wants feedback user: "Review my agent code for best practices" assistant: "I'll use the agent-reviewer to analyze your code for idempotence, isolation, security, and architecture patterns." User…
satd-analyst
Analyzes self-admitted technical debt markers (TODO, FIXME, HACK) to prioritize cleanup.
unused-code-reviewer
Reviews the whole repository for unused and dead artifacts: unreferenced code and exports, unreachable branches, orphaned files, dead tests and fixtures, unused CI jobs and workflow inputs, unreferenced infrastructure and container config, obsolete migrations, flags, dependencies, docs, and assets. Spawn when user…
code-reviewer
Reviews the codebase for correctness, style, patterns, and anti-patterns. Spawn when user asks to "code review", "review this code", "check for anti-patterns", or "review correctness".
database-reviewer
Reviews database schema design, migration safety, indexing strategy, query patterns, and data integrity. Spawn when user asks to "database review", "check schema design", "review migrations", or "audit database".
logging-reviewer
Reviews the codebase for logging and monitoring gaps. Spawn when user asks to "review logging", "check monitoring", "audit observability", or "find logging issues".