Back to skill

Security audit

Cold Outreach

Security checks for vulnerabilities and agentic risk

Overview

This skill is a cold-outreach writing guide with no executable code; its main caveat is to use prospect personalization lawfully and respectfully.

Before installing, treat this as a copywriting aid only. Use business-relevant, lawfully obtained prospect information, avoid sensitive personal data, honor opt-outs and unsubscribe requirements, and follow email, SMS, LinkedIn, GDPR, CCPA, CAN-SPAM, and local outreach rules.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs users to personalize outreach using prospect-specific signals such as company news, website details, and visible business problems, but it provides no warning about privacy, consent, lawful basis, or data-minimization obligations when collecting and using that information. This omission can normalize intrusive profiling or non-compliant outreach, increasing the risk of privacy violations, regulatory exposure, and reputational harm when users operationalize the guidance at scale.

Content

No source excerpt is available for this finding.