ClawHub
Back to skill

Security audit

agpair

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed control guide for using the agpair CLI with Antigravity and does not include hidden code, persistence, credential handling, or unrelated behavior.

Install this only if you use agpair and Antigravity for delegated coding work. Review task status and logs before approving or continuing delegated work, and avoid invoking broad delegation phrases unless you intend the CLI workflow to run.

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
86% confidence
Finding

The triggering guidance is broad enough to activate on common phrases like delegating work or inspecting status, which can cause the skill to run in situations the user did not specifically intend. In this skill, unintended activation is more sensitive because it can drive operational CLI actions against external task execution workflows, increasing the chance of mis-delegation or confusing control flow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
68% confidence
Finding

The manifest description hard-codes both English and Chinese trigger phrases, but does not explain whether multilingual behavior is optional, user-selected, or limited to a particular deployment context. This can create an implicit language/locale policy issue because the skill defines language behavior without documenting user opt-in or locale justification.

Content

No source excerpt is available for this finding.