ClawHub
Back to skill

Security audit

Agi Terminal Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent terminal-safety runbook and does not contain executable payloads or hidden high-impact behavior.

Install only if you want the agent to follow a conservative terminal-usage runbook. It may make the agent more deliberate about shell commands and confirmations, but the artifact does not add executable code or hidden access by itself.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

md
2) Verify the skill folder has `SKILL.md` and valid frontmatter.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

md
- “what/why/when/how” that is clearly specific to the skill

## What I will NOT do
- I will not run remote “install scripts” (e.g., `curl | sh`) without explicit user request and review.
- I will not paste or echo secrets into commands.
- I will not make destructive changes without confirming the exact file paths.

Static analysis

No suspicious patterns detected.