ClawHub
Back to skill

Security audit

ALab Project Controller

Security checks for vulnerabilities and agentic risk

Overview

This skill gives an agent ALab project-admin guidance, but the authority is disclosed, scoped to one existing project, and paired with credential separation and deletion safeguards.

Install this only if you intend to let the agent administer an existing ALab project. Provide the project admin key only through a private environment variable or secure stdin, and review destructive operations, worker launches, and project secret/config changes before allowing them.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
- `SKILL.md`: Canonical project-layer boundaries, credential rules, and coordination workflow.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This file presents the skill description and operational guidance entirely in Chinese, with no user opt-in or stated locale constraint. The policy requires flagging language or locale restrictions when the skill forces a specific language without offering a choice or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The default prompt encourages broad use of the skill to create experiments, launch worker sessions/subagents, and summarize evidence without clearly constraining when invocation is appropriate. Because this skill manages an existing ALab project using project admin capabilities and can spawn additional worker contexts, ambiguous trigger boundaries increase the risk of over-invocation, unintended privileged actions, or credential-adjacent misuse through prompt routing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.