Back to skill

Security audit

Find Leads

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a lead-generation skill with a privacy-transparency gap: targeting information and prospect identifiers may be sent to third-party services without clearly explaining those disclosures, so the verdict is suspicious.

Before installing, consider whether you are comfortable with targeting details and prospect identifiers being processed by third-party providers. The scanner recommends clear disclosure and informed approval before the first external query; the review was partial because some local references could not be resolved, so the evidence is incomplete.

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)

The workflow sends user-provided targeting information and contact identifiers to third-party services without a privacy disclosure in the approval plan.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow sends the user's targeting sentence and prospect identifiers through Scrollport to third-party search, enrichment, and email-verification providers, but its required approval plan explains spending rather than those disclosures. This can expose commercially sensitive targeting criteria or personal data without making the recipients and processing clear to the user. External processing is expected for this lead-generation task, and the skill includes spending and credential safeguards, so this is a privacy-transparency gap rather than evidence of malicious exfiltration.

Content

No source excerpt is available for this finding.