MCP-INDEX

◆ LLM analysis failed. Retry

RJL667/veilguardcritical

LibreChat + PII proxy + 8 MCP servers (76 tools) — AI workspace with sub-agents, tool forge, and document tools

This is an AI workspace orchestration system (Veilguard) that integrates LibreChat with a PII proxy and 8 MCP servers providing 76 tools. It enables s...

purpose: This is an AI workspace orchestration system (Veilthreat: network exposed

Python · ★ 0 · Jun 15, 2026 · ⚙ Jun 11, 2026 · GITHUB ↗

heuristic signalsaws.integration env.exposure auth.none shell.exec filesystem.read slack.integration filesystem.write network.http browser.automation postgres.access

RISK SCORE

0/ 100 risk

low findings+5

high findings+100

medium findings+75

critical findings+120

capped at100

Indicators — descriptive signals, not vulnerabilities

dynamic-importservices/forge/server.py:11import importlib.util

dynamic-importservices/forge/server.py:158 spec = importlib.util.spec_from_file_location(f"forge.{safe_name}", tool_file)

dynamic-importservices/forge/server.py:159 module = importlib.util.module_from_spec(spec)

dynamic-importservices/sub-agents/server.py:557 bridge.last_ping = __import__("time").time()

These are automated indicators of code characteristics detected by regex pattern matching. They are informational, not security verdicts. Some patterns (e.g. telegram, crypto-wallet) may reflect legitimate functionality.

Analysis failed

Findings are produced by automated LLM analysis and may include false positives or miss issues. Verify independently before acting.