Works with the AI Agents you already use
AgentGuard
Local security scanner for AI agent skills and MCP servers: tool poisoning, rug pulls, known CVEs, the lethal trifecta, and an experimental AI semantic check (--deep).
Free
AgentGuard
Example session with this skill installed
Audit the skills in ./ejemplos and my MCP config at claude_desktop_config.json. Give me a report.
- Read your context and instructions
- Compiled the agentguard
I ran agentguard audit --skills ejemplos --config claude_desktop_config.json --out agentguard-report.md --lang en.
Overall risk: High. 9 findings: 1 Critical, 3 High, 3 Medium, 2 Info.
| Severity | Finding | Where | How to fix |
|---|---|---|---|
| Critical | CVE-2025-6514 in mcp-remote 0.1.15 (OS command injection via untrusted MCP server connections) | npm | Upgrade mcp-remote to 0.1.16 |
| High | Asks to hide something from the user («Do not tell the user») | ejemplos/malicioso_tools.json:1 | Treat the tool as malicious: uninstall and report it |
| High | Secret + external send (possible theft) («.ssh → send it to https://») | ejemplos/malicioso_tools.json:1 | Uninstall it, rotate the keys it mentions, report it |
| High | Lethal trifecta: filesystem/git read private data, fetch brings in untrusted content and sends data out | config · global | Remove one leg (e.g. fetch), or restrict docker's tools to read-only |
| Medium | Mentions secrets (2 times) | ejemplos/malicioso_tools.json | Confirm it only explains where to put a key |
| Medium | Sends data to an external URL | ejemplos/malicioso_tools.json:1 | Confirm the domain belongs to the author |
| Medium | Urgency tags aimed at the model («<IMPORTANT>») | ejemplos/malicioso_tools.json:1 | Remove <IMPORTANT>-style tags |
| Info | mcp-server-fetch version not pinned (runs the latest) | config · fetch | Pin the exact version |
| Info | docker: command can't be checked against OSV | config · docker | Review it manually |
Next steps
- Uninstall the tool in
malicioso_tools.jsonnow; it tries to read SSH keys and send them out. - Upgrade mcp-remote to 0.1.16.
- Break the trifecta by removing fetch or limiting docker.
- Once clean, run
agentguard lock <folder> --lang enso future changes get caught.
The full report, with a manual-review checklist, is saved in agentguard-report.md.
Connects securely to your tools. The creator never sees your data.
About this skill
Security reviews for AI agent tools are often overlooked until a data breach occurs. This skill provides a local security layer to audit SKILL.md files, plugins, and MCP servers for malicious instructions or vulnerabilities. It identifies prompt injection risks, tool poisoning, and the "lethal trifecta" where an agent has access to private data, untrusted content, and an outbound communication channel simultaneously.
What it does
- Prompt injection detection flags hidden instructions or tool poisoning in skill definitions.
- Semantic check (experimental) with --deep: an AI model judges each skill's intent to catch injections disguised as normal steps. Needs ANTHROPIC_API_KEY and sends the text to Anthropic.
- Vulnerability scanning queries OSV.dev to find known CVEs in installed MCP servers.
- Integrity verification creates a lockfile for skill folders to detect unauthorized changes or "rug pulls."
- Exfiltration analysis flags MCP configurations that combine private data, untrusted content and an outbound channel.
- Automated reporting generates Markdown audit reports summarizing findings by severity.
How it works
- Scan a specific skill or plugin folder to detect immediate prompt-based threats. Add --deep for the AI semantic check (--deep-dry-run shows what would be sent, without sending anything).
- Lock and Verify to baseline a trusted tool and catch changes during updates.
- CVE Check to cross-reference installed MCP tools against public vulnerability databases.
- Trifecta Audit to analyze the systemic risk of your specific MCP configuration.
Frameworks & tools
Built for any agentic environment using MCP servers or local skill definitions. Requires the agentguard-scan Python package (0.5.0+ for --deep).
Why this beats prompting it yourself
Fixed rules and the semantic check run the same way every time, with an injection-resistant judge prompt, strict JSON output and quotes verified against the original text. CVE lookups use a live public database that a standard prompt cannot access reliably.
Use cases
- Auditing a new third-party skill downloaded from a marketplace before installation.
- Checking for CVEs in a complex MCP configuration with multiple active tools.
- Detecting if a previously safe tool was modified to include malicious instructions.
- Hardening CI/CD pipelines with the agentguard GitHub Action, failing builds on high-severity findings.
Known limitations
Requires Python 3.9+ and the agentguard-scan package. Network access is needed for CVE lookups (audit --offline skips them). On an independent blind set (Skill-Inject, 34 attacks), fixed rules rated 2 HIGH (6%); with --deep, 31 of 34 (91%). --deep is experimental and noisy on long real-world skills (2.6% HIGH, all false on review), so check each finding by hand. No findings does not prove a skill is safe.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
Requires Python 3.9+ and the agentguard-scan package. Network access is needed for CVE lookups (audit --offline skips them). On an independent blind set (Skill-Inject, 34 attacks), fixed rules rated 2 HIGH (6%); with --deep, 31 of 34 (91%). --deep is experimental and noisy on long real-world skills (2.6% HIGH, all false on review), so check each finding by hand. No findings does not prove a skill is safe.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
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
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 6 days ago
- Free with an Agensi account
- Accounts
Osv
- Software
Python 3.9+agentguard-scan (pip)
Permissions
Allowed Hosts
File Scopes
Terminal runs the agentguard CLI. Read Files scans skills and MCP configs. Write Files saves the lock file and the Markdown report. Network Access only queries OSV.dev for known CVEs (sends package name, ecosystem and version); audit --offline skips it. No server is executed.