ClawHub
Back to skill

Security audit

Workflow Refactor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only workflow simplification framework with disclosed compliance safeguards and no executable behavior.

Before installing, treat the skill as a planning framework rather than domain expertise. For regulated, legal, financial, medical, security, or safety-critical workflows, keep human review and required compliance checks in place.

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

Claiming applicability to 'any domain' without clear scope boundaries makes the skill prone to activation in sensitive areas like legal, medical, finance, or security workflows where generic simplification advice may be unsafe. Even though the skill mentions preserving compliance, ambiguous scope increases the chance of misuse or accidental application beyond the author's competence assumptions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Claiming applicability to 'any domain' without clear scope boundaries makes the skill prone to activation in sensitive areas like legal, medical, finance, or security workflows where generic simplification advice may be unsafe. Even though the skill mentions preserving compliance, ambiguous scope increases the chance of misuse or accidental application beyond the author's competence assumptions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.