ClawHub
Back to skill

Security audit

Ravi login

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Ravi login helper, but users should understand it handles stored auth keys, saved site credentials, and OTP inbox access.

Install only if you want the agent to manage Ravi-based signups and logins. Use it on a trusted machine because it can create and retrieve website credentials, use stored Ravi auth material, and inspect Ravi SMS/email inbox content for verification codes or links.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to run an auth flow and notes that keys are stored in ~/.ravi/config.json, but it does not clearly warn the user that long-lived authentication material and site credentials will be persisted on disk. In a login/identity-management skill, this omission is security-relevant because it can lead to unintended local secret exposure, especially on shared hosts, synced home directories, or insecure endpoints.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs the agent to read SMS and email inbox content to retrieve OTPs and verification links, but it does not clearly warn that this may expose sensitive message contents beyond the one-time code. In context, this skill is specifically designed to access login factors and verification messages, so the lack of a privacy and scope warning increases the risk of over-collection or inadvertent disclosure of sensitive communications.

Static analysis

No suspicious patterns detected.