ClawHub
Back to skill

Security audit

statusline

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only guide for configuring a CLI status line, with disclosed local command execution and session metadata handling.

Before installing, review any script or inline command you configure for the status line. It will run locally on conversation updates and receive paths and session metadata, so avoid third-party, networked, or logging commands unless you have inspected 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation text says to use the skill when the user 'mentions status line' or 'wants to add session context above the prompt,' which is broad and lacks clear boundaries for when the skill should or should not activate. It does not provide exclusion conditions or negative examples, increasing the risk of unintended invocation from general discussion about prompts or UI customization.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs users to configure a command that is executed locally on every conversation update and fed session metadata on stdin, including transcript paths, working directory, project paths, and worktree details. Without an upfront warning, users may unknowingly pipe sensitive local metadata into third-party scripts or inline commands, increasing the risk of privacy leakage or exfiltration through status line integrations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.