Back to search
? Not scanned yet

@dj_abstract/mcp-audit

Author abregoarthur-star
Scanned 25d ago

Security auditor for Model Context Protocol (MCP) servers — scans tool definitions for prompt injection, tool poisoning, unsafe combinations, and other AI-native vulnerabilities.

npm

Versions

0.4.0
Apr 20, 2026
0.3.1
Apr 18, 2026
0.3.0
Apr 18, 2026
0.2.0
Apr 18, 2026
0.1.0
Apr 18, 2026

Tools 0

No tools indexed yet.

Permissions 4

network Server uses network capabilities via: fetch()
medium
filesystem Server uses filesystem capabilities via: fs/promises
low
shell Server uses shell capabilities via: child_process
high
env_vars Server uses env_vars capabilities via: process.env
low

Scan Findings 12

info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.29.0 (GHSA-6qxp-vccf-f47h) dependency_analyzer · 95%
info
package.json metadata manifest_parser · 100%
info
Transport: streamable-http manifest_parser · 80%
info
Required env vars (1) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
medium
Permission: network access detected permission_analyzer · 70%
low
Permission: filesystem access detected permission_analyzer · 90%
high
Permission: shell access detected permission_analyzer · 95%
low
Permission: env_vars access detected permission_analyzer · 90%
info
SBOM generated: 92 components sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%