ClawHub
Back to skill

Security audit

competitors

Security checks for vulnerabilities and agentic risk

Overview

This skill is a marketing-content guide for competitor comparison pages and does not contain hidden execution, persistence, or data exfiltration behavior.

Installers should understand that this skill may use internal product-marketing context when available and should keep competitor claims factual and reviewed, but the artifact does not show malicious or unsafe system behavior.

A.I.G

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

SkillSpector

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger description is very broad and includes many generic competitor-related phrases such as 'battle card,' 'competitor teardown,' and 'how do we compare to X,' which can cause the skill to activate outside its intended workflow of creating external competitor comparison pages. Over-broad activation can route unrelated or more sensitive requests into this skill, producing off-target outputs, increasing the chance of inappropriate disclosure or misleading content generation in contexts like internal strategy or sales collateral.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The eval explicitly expects the skill to trigger on vague, casual phrasing for a competitor-content workflow, which broadens activation beyond tightly scoped intents. Over-broad triggering can cause the wrong skill to engage on adjacent requests, leading to misleading competitive content generation, policy bypass in routing, or failure to hand off to more appropriate skills such as sales-enablement.

Content

No source excerpt is available for this finding.