← Back to search

@exfil/canary

exfil-hq Scanned 2h ago

Transparent MCP proxy that watermarks agent tool responses and blocks data exfiltration caused by prompt injection.

npm ↗
? Not scanned yet

Versions

1.0.0latest
Mar 21, 2026

Tools 0

No tools indexed yet.

Permissions 3

network medium
Server uses network capabilities via: fetch()
shell high
Server uses shell capabilities via: spawn()
env_vars low
Server uses env_vars capabilities via: process.env

Scan Findings 15

high
Hardcoded API key in exfil-hq-Canary-b787977/src/__tests__/entities.test.ts auth_checker · 90%
medium
OAuth implementation without PKCE auth_checker · 75%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.0.0 (GHSA-w48q-cv73-mx4w) dependency_analyzer · 95%
medium
Vulnerable dependency: vitest@2.1.9 (GHSA-5xrq-8626-4rwp) dependency_analyzer · 95%
medium
Vulnerable dependency: vitest@2.1.9 (GHSA-82fw-gwwq-j7x9) dependency_analyzer · 95%
info
package.json metadata manifest_parser · 100%
info
Transport: stdio manifest_parser · 90%
info
Required env vars (8) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
medium
Permission: network access detected permission_analyzer · 70%
high
Permission: shell access detected permission_analyzer · 90%
low
Permission: env_vars access detected permission_analyzer · 90%
info
SBOM generated: 4 components sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%