ClawHub
Back to skill

Security audit

Campaign Management

Security checks for vulnerabilities and agentic risk

Overview

This campaign-management skill is coherent, but its outreach/autonomous modes imply sending messages and handling personal contact data without enough consent, privacy, or approval detail.

Install only if you are comfortable with a skill that can manage lead lists, generate contact reports, and potentially operate outreach workflows. Before using outreach or autonomous mode, require manual review before any email, LinkedIn message, or social post is sent, confirm which account/domain is used, and define privacy/retention rules for enriched contact data.

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 (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The configuration supports outreach and autonomous modes, includes email provider settings, rate limits, and outbox generation, but does not clearly warn that the skill may draft or send messages on the user's behalf. In this context, silent or poorly disclosed outbound messaging is especially risky because it can cause unauthorized communications, spam/compliance issues, reputational harm, and unintended use of connected accounts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly manages lead discovery, enrichment, and report generation containing personal contact data, but it does not clearly warn users that it will generate, store, and track personal data such as emails and phone numbers. In a campaign-management context, this increases the risk of privacy, compliance, and consent violations because users may invoke the skill without understanding the data handling involved.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The sample configuration fixes the schedule to Asia/Jerusalem and a Sun-Thu workweek, which reflects a specific locale. Because the documentation does not present this as optional, user-selectable, or region-specific, it appears to impose a locale default without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.