ClawHub
Back to skill

Security audit

ORCID

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ORCID lookup helper that uses OOMOL's CLI to search and read public ORCID data, with no artifact-backed evidence of hidden or destructive behavior.

Before installing, understand that this skill depends on the OOMOL oo CLI and an OOMOL-connected ORCID account. It should be used for public ORCID lookups; if future connector schemas show write or destructive ORCID actions, require explicit confirmation before running them.

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest and top-level description claim the skill is only for searching and reading ORCID data, but the body of the skill explicitly discusses possible [write] and [destructive] actions. This mismatch weakens security expectations and could cause a caller, reviewer, or policy layer to treat the skill as read-only when the underlying connector may expose state-changing capabilities.

Static analysis

No suspicious patterns detected.