litterbox
mcp5.0.0A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.
By BlackSnufkin | 1 findings | Scanned 5/30/2026 | tooltrust-scanner/v0.3.13 | 1.4k
Risk Summary
Safe With Normal ControlsEmbedded MCP is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Scan Incomplete
No tool definitions were found in this repository. The grade shown does not reflect actual security analysis — the scanner could not enumerate this server's tools. Verify the repo contains a valid MCP manifest and re-scan.
Security Findings (1)
Embedded MCP server detected in python source, but tool enumeration was not possible. Manual review is required for auth, scope, and input validation.
Fix: Source-level MCP SDK usage was detected, but tools could not be enumerated statically. Run a sandboxed live scan if possible and manually review auth, scope, and input validation before trusting this server.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y litterbox"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)