More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ai Security Auditor

    2

    Your AI agent has access to 12 tools, reads from a vector database, and executes shell commands.

    Free

    24 usesSecurity scanned
    ai-security-auditor

    ai-security-auditor

    Example session with this skill installed

    "Audit my agent configuration — it uses 5 MCP servers and scrapes web content"

    • Read your context and instructions
    • Compiled the ai-security-auditor
    AI SECURITY AUDIT REPORT
    ════════════════════════
    Agent: content-researcher
    Overall Risk: HIGH (2 Critical, 4 High, 3 Medium)
    
    ID  Severity  Category     Finding                                       Remediation
    ──  ────────  ───────────  ────────────────────────────────────────────  ─────────────────────────────────────────
    F1  CRITICAL  Injection    Web scraper output concatenated into context  Add content delimiter tokens and strip
                               unsanitized                                   instruction patterns
    F2  CRITICAL  Agency       Terminal tool has unrestricted shell access   Restrict to command allowlist (git, npm,
                                                                             python)
    F3       HIGH  Leakage  API key hardcoded in system  Move to env var
                            prompt line 23               $AGENT_API_KEY via secret
    ───────  ────  ───────  ───────────────────────────  ─────────────────────────
    manager
    F4  HIGH      Permissions  MCP filesystem server has write access to /   Restrict to project directory with path
                                                                             allowlist
    
    Priority actions: [1] Sanitize web output before context injection
    [2] Restrict terminal to allowlist [3] Rotate and remove hardcoded key
    

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The Problem

    Your AI agent has access to 12 tools, reads from a vector database, and executes shell commands. The system prompt was copied from a blog post. A malicious user discovers that crafted input causes the agent to dump environment variables into a public channel. You don't find out days later. Prompt injection is the #1 attack vector against AI agents — and most teams have zero defensive tooling beyond "trust the model."

    What You Get

    • Scan prompt templates for injection vectors — detect direct concatenation of user input into system prompts, insufficient role separation, XML/markdown tag injection, and recursive override patterns across six attack categories
    • Audit tool permission boundaries — map every MCP server and tool integration to a permission matrix (read/write/execute/network) with risk-level classification from LOW to CRITICAL
    • Detect data leakage paths — find hardcoded API keys in system prompts, sensitive data persisting in conversation history, context window overexposure, and tool output that returns more data than the agent needs
    • Evaluate excessive agency — classify every autonomous action on an escalation ladder (READ_ONLY through FULL_EXECUTE) and flag missing human-in-the-loop gates with blast-radius analysis
    • Assess RAG pipeline security — check vector database authentication, document ingestion sanitization, retrieval relevance scoring, and context assembly trust-weighting for poisoned-document attacks
    • Generate structured audit findings — CRITICAL/HIGH/MEDIUM/LOW severity with specific line references, OWASP LLM category mapping, and prioritized remediation steps that include before/after code examples

    Why This Beats Prompting It Yourself

    Asking an agent "is my prompt secure?" returns generic advice about role separation. But it won't trace the full data flow from a tool's untrusted output through your RAG retrieval into the LLM context, identifying that a poisoned document in your vector DB could override system instructions. This skill maps the complete attack surface across six phases with pattern-matching precision — not vibes.

    Example Session

    You: "Audit my agent configuration — it uses 5 MCP servers and scrapes web content"

    Agent:

    AI SECURITY AUDIT REPORT
    ════════════════════════
    Agent: content-researcher
    Overall Risk: HIGH (2 Critical, 4 High, 3 Medium)
    
    ID  Severity  Category     Finding                                       Remediation
    ──  ────────  ───────────  ────────────────────────────────────────────  ─────────────────────────────────────────
    F1  CRITICAL  Injection    Web scraper output concatenated into context  Add content delimiter tokens and strip
                               unsanitized                                   instruction patterns
    F2  CRITICAL  Agency       Terminal tool has unrestricted shell access   Restrict to command allowlist (git, npm,
                                                                             python)
    F3       HIGH  Leakage  API key hardcoded in system  Move to env var
                            prompt line 23               $AGENT_API_KEY via secret
    ───────  ────  ───────  ───────────────────────────  ─────────────────────────
    manager
    F4  HIGH      Permissions  MCP filesystem server has write access to /   Restrict to project directory with path
                                                                             allowlist
    
    Priority actions: [1] Sanitize web output before context injection
    [2] Restrict terminal to allowlist [3] Rotate and remove hardcoded key
    

    Use Cases

    • Pre-deployment security review of any AI agent or LLM-powered application
    • Evaluating third-party MCP servers before adding them to your agent's toolset
    • Post-incident forensics after a suspected injection attack on your agent
    • Compliance documentation for regulated industries (finance, healthcare, government)
    • Hardening agent configurations during security sprints or red-team exercises
    • Training new team members on secure prompt engineering patterns with real examples

    Known Limitations

    This is static analysis of configuration files — it cannot detect dynamic attacks during live user interaction. Multi-agent trust boundaries and cascading permission escalation are partially covered but require manual review for complex orchestration patterns. Non-English skill files may have undetected issues since patterns are English-focused.

    Upgrade Path

    Free audits one agent surface in conversation against the OWASP LLM Top 10. AI Security Auditor Pro ($9.99 one-time) batch-scans a skill library, maps findings to OWASP LLM Top 10, emits SARIF for GitHub Code Scanning, and auto-generates remediation patches.

    Upgrade when you maintain more than a handful of skills or need a merge-gate artifact:

    https://www.agensi.io/skills/ai-security-auditor-pro

    This is static analysis of configuration files — it cannot detect dynamic attacks during live user interaction. Multi-agent trust boundaries and cascading permission escalation are partially covered but require manual review for complex orchestration patterns. Non-English skill files may have undetected issues since patterns are English-focused.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    24 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Listed5 months ago
    Updated18 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the detection of prompt injection, data leakage, and excessive tool permissions by applying the OWASP Top 10 for LLM Applications directly to your agent's codebase and MCP configurations.

    It is framework-agnostic and supports all major AI agent frameworks, as well as any integration utilizing the Model Context Protocol (MCP) for tool and resource management.

    You receive the core auditing engine, a set of pre-configured security test suites, and a reporting module that generates professional documentation for compliance reviews.

    Implementation is straightforward; the skill is designed to plug into your existing development environment or CI/CD pipeline to scan your prompt templates and tool definitions.

    Yes, the auditor is specifically designed to scan RAG pipelines for indirect injection threats where malicious content might be pulled from external data sources into the LLM context.

    The skill is updated regularly to reflect the evolving threat landscape, including the latest prompt injection techniques and updated security standards for 2025 and beyond.

    New in Security