mcp-oauth-remote-gateway
What this skill does
This skill is a utility for handling OAuth on remote MCP (Machine Check Point) servers, specifically for headless gateways. It manually performs the OAuth flow and stores tokens in a format expected b
github/nousresearch - Privilege Escalation - 228.4k stars
Threat analysis
Skill info
pkg:github/NousResearch/hermes-agent@49c6323?skill=mcp-oauth-remote-gatewayAssessments (2)
Privilege Escalation
Privilege Escalation via local-llm-review
scripts/diagnose-oauth-mcp.py
The script handles OAuth tokens and interacts with remote MCP servers. If not properly secured, it could potentially be used to exfiltrate sensitive tokens or credentials, especially if the script is Insecure Token Handling
Insecure Token Handling via local-llm-review
scripts/diagnose-oauth-mcp.py
The script writes tokens to disk with specific permissions (`0600`), but if the script is not properly secured or if the environment is compromised, there is a risk of token leakage or unauthorized acBadge
Add the Anomity scan badge for mcp-oauth-remote-gateway to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of mcp-oauth-remote-gateway? Report an issue or request a rescan.
