ClawHub
Back to skill

Security audit

Trust

Security checks for vulnerabilities and agentic risk

Overview

This is a plain guidance skill for analyzing and repairing trust, with no code, credential use, persistence, or hidden execution behavior.

Before installing, understand that this skill may frame a wide range of interpersonal or business-confidence questions through a trust lens. For legal, HR, compliance, clinical, security, or regulated decisions, use appropriate professional or domain-specific guidance instead of relying on this skill alone.

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
90% confidence
Finding

The trigger conditions are broad and overlap with many ordinary advice, communication, and relationship queries, which can cause the skill to activate outside its intended scope. Overbroad invocation increases the chance that more appropriate domain-specific skills or safety policies are bypassed, especially when requests touch adjacent areas like HR, legal, compliance, or sensitive interpersonal matters.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The sample trigger phrases are common conversational expressions that could match a wide range of general advice requests, making unintended invocation likely. If the orchestration system uses these examples for routing, the skill may be selected too often and provide trust-framed guidance where a different, more precise skill or stronger safeguards should apply.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.