ClawHub
Back to skill

Security audit

Intent Align

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed project-orchestration workflow that can coordinate local, GitHub, and tracker work, but I found no hidden execution, persistence, exfiltration, or deceptive behavior.

Install this only if you want an agent to coordinate multi-step project work. Expect it to create local planning artifacts, potentially edit project files, run project verification commands, and update GitHub or tracker records when you grant the relevant access. Use stricter confirmation settings for sensitive repositories or public-facing trackers.

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
Confidence
90% confidence
Finding
The skill description is broadly phrased around coding, repos, PRs, issues, multi-phase delivery, and coordination across environments, which can cause over-triggering for many general software tasks. An overly broad activation surface increases the chance this orchestration skill is invoked in contexts where a narrower, safer skill should apply, potentially expanding tool use and autonomy unnecessarily.

Missing User Warnings

Low
Confidence
89% confidence
Finding
The adapter explicitly states it can create or update files and run local verification commands, but the text provides no user-facing warning, confirmation requirement, or safety boundary around these impactful actions. In an agent skill, this increases the chance of unintended filesystem changes or command execution occurring without sufficiently explicit user awareness, especially across local or multi-repo workspaces.

Static analysis

No suspicious patterns detected.