ClawHub
Back to skill

Security audit

Ravi email-writing

Security checks for vulnerabilities and agentic risk

Overview

The skill is only an email-writing guide, but it explicitly encourages emails that hide AI involvement, which users should review before using for outreach.

Review this skill before installing if your organization requires AI disclosure or has rules against deceptive outreach. It has no code execution surface, but its writing guidance should be adjusted or used carefully for customer, sales, recruiting, legal, or other sensitive email contexts.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to write emails that appear to come from a real person rather than an AI, and later advises against including 'Sent by AI' disclosures. In the context of an email composition skill, this increases the risk of deceptive impersonation, social engineering, and undisclosed AI-generated outreach, especially when paired with a sending skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.