Back to skill

Security audit

Lead Gen

Security checks for vulnerabilities and agentic risk

Overview

The skill is a transparent B2B lead-generation helper, but it needs review because it encourages collecting and estimating identifiable contact emails without privacy or acceptable-use limits.

Review this skill before installing if you will use it for real outreach. Limit it to authorized B2B prospecting, follow applicable privacy laws and site terms, avoid personal or sensitive data, do not bulk-harvest or guess emails unless your policy permits it, and store any generated lead lists only as long as needed.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill invokes local code execution behavior (scripts/enrich_leads.py) and the static analyzer detected file-write capability, but the manifest does not declare any tool scope or permissions. That mismatch weakens sandboxing and reviewability, making it easier for the skill to perform filesystem-affecting actions without explicit operator awareness.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill directs collection, scraping, enrichment, and estimated email generation for identifiable business contacts without any privacy, consent, retention, or legal-use guidance. In context, this increases the chance of improper personal data processing, terms-of-service violations, and downstream misuse of scraped contact information at scale.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The playbook explicitly instructs users to derive employee email patterns and harvest addresses from public sources without any guardrails around consent, privacy law, platform terms, or acceptable-use limits. In a lead-generation skill, this materially increases the likelihood of bulk contact harvesting, unwanted outreach, and misuse of personal/work contact data, making the omission operationally dangerous rather than merely informational.

Content

No source excerpt is available for this finding.