ClawHub
Back to skill

Security audit

OpenClaw Email Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill provides audit-focused email operations guidance with clear approval gates and no executable install or persistence behavior.

Installers should still treat email exports, contact lists, suppression files, logs, DNS settings, and live sends as sensitive. Use the skill for audit-style campaign operations and require explicit human approval before any production email-system change.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description says to use the skill whenever an AI agent needs to "plan, review, implement, audit, or improve email work" and then lists broad triggers like "transparent email operations." In a markdown/manifest context, this activation guidance is expansive and lacks clear exclusions beyond a later generic fit check, which could cause unintended invocation for ordinary email-assistance requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.