Back to skill

Security audit

google-ads-negative-keyword-list

Security checks for vulnerabilities and agentic risk

Overview

The bundled script processes local search reports without accessing Google Ads, although it does not automate the complete advertised workflow.

Use a CSV containing a search_term column; the advertised YAML quickstart does not work as written. Independently review proposed exclusions and account limits before manually uploading anything. Choose a dedicated output directory because duplicates.md is overwritten. The optional Windows application requires a separate security review.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code implements duplicate detection and reporting, which supports only a portion of the declared workflow. Its sole output is a duplicate report, not the promised actionable negative keyword list. The guardrails are static text and do not implement keyword suitability checks or account-limit validation. No undeclared network access or Google Ads account modification is present.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The skill produces only a duplicate report, not the negative keyword list and account-limit checks promised by its manifest.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest promises a deduplicated negative keyword list with match types, application levels, and account limits checked. The implementation only groups search terms by normalized text and writes duplicate counts and examples to duplicates.md; it neither outputs the unique keyword list nor determines match types, application levels, or account-limit compliance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.