ClawHub
Back to skill

Security audit

Agi Term Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent power-user shortcut that runs the exact terminal command the user types, with clear warnings about the risks.

Install only if you intentionally want a raw terminal shortcut. Treat `/term` commands like commands typed into your own shell: avoid secrets in command lines, double-check destructive paths, and rely on sandboxing where possible.

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 (1)

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 52)May include surrounding context.

md
1) Prefer read-only commands unless you *mean* to change state.
2) Avoid secrets in command lines (tokens, API keys, cookies).
3) Avoid remote execution one-liners:
   - no `curl ... | sh`
   - no “download and execute” pipelines
4) If the command could delete or overwrite files, slow down and double-check paths.

Static analysis

No suspicious patterns detected.