Back to skill

Security audit

Work Productivity Multi Search Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill provides ordinary workflow guidance, though its broad keywords may cause unexpected activation.

Expect a planning helper rather than an implemented multi-engine search tool. Prefer explicit invocation or narrower keywords if it activates on unrelated requests.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

The usage keywords include common terms without activation constraints.

Medium
Category
Trigger Abuse
Confidence
93% confidence
Finding

The usage section lists broad keywords such as search, global, supports, and bug fix, which occur in everyday requests unrelated to this skill. It does not constrain these keywords to a Multi Search Engine workflow or explicitly exclude unrelated uses, creating a risk of unintended activation.

Content

No source excerpt is available for this finding.

Activation keywords and invocation criteria are overly broad and can match unrelated requests.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger list includes generic words such as multi, search, engine, global, and supports, without requiring a Multi Search Engine workflow context. The description at L04 also permits activation for generic workflow or implementation support, and no exclusion conditions prevent unintended invocation.

Content

No source excerpt is available for this finding.

Activation keywords include common, context-free words that can trigger unrelated requests.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger list includes broad terms such as search, engine, global, supports, and integration, without requiring a Multi Search Engine or Clawhub context. Line L04 also explicitly activates the skill for several generic keywords, so ordinary requests unrelated to this workflow could invoke it.

Content

No source excerpt is available for this finding.

Implicit invocation is enabled, but the description does not define a clear activation scope.

Medium
Category
Trigger Abuse
Confidence
92% confidence
Finding

The truncated description and malformed default prompt describe demand for multi-search workflows and generic bug fixing rather than specifying when this skill should activate. With implicit invocation enabled, these ambiguous descriptions provide insufficient boundaries to distinguish relevant requests from unrelated productivity or debugging tasks.

Content

No source excerpt is available for this finding.

Activation keywords include broad, everyday terms unrelated to a specific multi-search workflow.

Low
Category
Trigger Abuse
Confidence
96% confidence
Finding

The Usage section lists generic keywords such as 'supports', 'global', 'integration', and 'bug fix' without requiring a multi-search context. These terms overlap with many unrelated requests, and the trigger sentences provide no exclusion conditions to prevent unintended invocation.

Content

No source excerpt is available for this finding.

Usage keywords include broad terms without constraints tying activation to Multi Search Engine workflows.

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

The usage signals include standalone terms such as "multi", "search", "global", "supports", and "bug fix", which occur in many unrelated requests. Although the example trigger sentences mention Multi Search Engine, the file does not specify that keyword matches require that context or provide exclusions.

Content

No source excerpt is available for this finding.