ClawHub
Back to skill

Security audit

Evervault

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Evervault connector wrapper, but users should be careful because it can decrypt/encrypt sensitive data and its fallback CLI install uses remote install scripts.

Install only if you are comfortable using OOMOL as the connector intermediary for Evervault data. Do not run the remote installer commands unless you trust OOMOL's CLI distribution path, and review exact payloads before approving encrypt or decrypt actions because decrypted values may expose sensitive plaintext.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs the agent to install software via a remote script piped directly into a shell (curl ... | bash), which executes unverified code fetched at runtime. If the remote host, transport, or distribution pipeline is compromised, this can lead to arbitrary code execution on the user's machine or runner with the agent's privileges.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation text says to use this skill for ANY Evervault request and instead of calling the API directly, which is overly broad routing guidance. This can cause the agent to invoke the skill on any Evervault mention without sufficient task-specific validation, increasing the chance of unintended connector use and risky write operations such as encryption or decryption being triggered in the wrong context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.