Corpus

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Corpus integration that discloses its API-token use and only performs purpose-aligned Corpus read/write actions.

Install only if you want OpenClaw to access your Corpus account. Keep CORPUS_API_TOKEN private, prefer the default Corpus API base URL unless you trust another endpoint, and review any save-url, reminder, or repository-edit plan before confirming it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill uses sensitive environment data (`CORPUS_API_TOKEN`) and network access to a remote API, but it does not declare explicit permissions for those capabilities. That creates a transparency and policy-enforcement gap: users or platforms cannot accurately reason about what the skill can access, and a compromised or modified implementation could exfiltrate tokens or user Corpus data over the network. In this context the behavior is expected for the skill’s purpose, but the missing declaration still weakens security controls and auditability.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal