ClawHub
Back to skill

Security audit

Clawqueue Skill V6

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only ClawQueue integration whose GitHub issue, worker, credential, log, and state behaviors are disclosed and aligned with its queue-management purpose.

Install only if you intend to let ClawQueue operate on your GitHub issues, project boards, and local repositories. Keep clawqueue.private.json private, limit GitHub and LLM tokens to the minimum scopes needed, and review the configured workflow policy before running scheduler or retry commands.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file documents a private configuration file containing API credentials, LLM keys, and endpoint overrides, but does not provide any caution about sensitive secret handling, storage, or exposure. Under the markdown-specific warning criteria, this is a privacy- and security-relevant behavior that should be disclosed to users.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.