Back to skill

Security audit

Work Productivity Ontology Typed Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: the completed scans found no executable scripts and one low-probability concern about broad activation keywords.

The verdict is benign, but broad activation wording may lead to unintended use outside ontology workflows. Consider whether that scope suits you before installing.

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 (5)

Activation uses broad standalone keywords and generic requests without limiting them to ontology workflows.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger keywords include everyday terms such as "creating", "memory", "knowledge", and "structured", which can match requests unrelated to this skill. The description at L04 also permits activation for generic workflow, checklist, or analysis requests, and the trigger examples provide no exclusions or requirement that these terms occur in an ontology-specific context.

Content

No source excerpt is available for this finding.

Generic trigger keywords can activate the skill outside ontology-workflow tasks.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger list includes broad words such as creating, memory, knowledge, and graph without requiring an ontology-workflow context. These terms occur in many unrelated requests, and the skill provides no exclusion conditions to prevent unintended activation.

Content

No source excerpt is available for this finding.

Implicit invocation is enabled without a clear activation scope.

Medium
Category
Trigger Abuse
Confidence
90% confidence
Finding

The description and default prompt contain incomplete statements about demand for ontology-style workflows rather than defining which user requests this skill handles. With implicit invocation enabled, references to broad tasks such as fixing bugs or hardening do not clearly distinguish intended requests from unrelated development work.

Content

No source excerpt is available for this finding.

Usage keywords include broad terms without explicit activation constraints.

Low
Category
Trigger Abuse
Confidence
88% confidence
Finding

Keywords such as creating, memory, and bug fix overlap with many requests unrelated to ontology workflows. Although the subsequent trigger sentences are more specific, the README does not clarify that these keywords must occur within an ontology-related request or provide exclusions.

Content

No source excerpt is available for this finding.

The usage keywords include broad terms such as `creating`, `memory`, `knowledge`, and `bug fix` without restricting them to ontology workflows.

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

These keywords overlap with routine requests unrelated to ontology-based workflows and could cause unintended skill invocation. Although the example trigger sentences are domain-specific, the usage section does not clarify whether the standalone keywords require the same context or specify exclusions.

Content

No source excerpt is available for this finding.