Back to skill

Security audit

LeadShield Contact Form & B2B Solicitation Blocker

Security checks for vulnerabilities and agentic risk

Overview

The skill’s spam screening, site access, and rule changes fit its stated purpose and include clear user controls.

Screening sends submitted content to LeadShield’s external service. Review its privacy, retention, and pricing terms; use synthetic test messages, exclude unnecessary sensitive information, and grant access only to intended sites.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

Screening instructions omit disclosure that submission content is sent to a third-party service.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The screening instructions encourage submitting message content to an externally hosted LeadShield service without explicitly disclosing that data transfer or requiring sensitive-data minimization. Contact form messages can contain personal or confidential information, so an agent could transmit that information without the user understanding the destination; the explicit external-service setup and site authorization mitigate this concern but do not establish informed permission for every submission.

Content

No source excerpt is available for this finding.