ClawHub
Back to skill

Security audit

Xiaobai Workflow Enforcer

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malicious, but it broadly forces agent workflow and workspace file updates in ways users should review before installing.

Install only if you want an agent to slow down and enforce design, planning, test-first, and verification gates across coding work. Be aware it may cause extra approvals, refuse to continue without plans or tests, and create design/checkpoint files unless your agent applies user-instruction precedence and proportional exceptions.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:11
Finding

Mandatory Instructions Hijack the Agent's Task Workflow

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 182)May include surrounding context.

md
| No plan | Don't execute, create plan first |
| No test | Don't write function, write test first |
| Test failing | Don't continue, fix the code |
| No verification | Don't say "done", verify first |

## Integration with Other Xiaobai Skills

Static analysis

No suspicious patterns detected.