ClawHub
Back to skill

Security audit

CLI builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward CLI-building guide with examples and a scaffold script, with no evidence of hidden control, data theft, or unsafe persistence.

Install is reasonable for CLI development. Before running the scaffold script, choose a new project directory and review generated files; when adapting packaging examples, pin dependency and npx package versions for reproducible builds.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation scope is very broad, covering not just CLI framework design but also terminal colors, piping, packaging, config management, testing, and general cross-platform terminal behavior. Overly broad activation can cause the skill to trigger on many common development requests, increasing the chance that expansive instructions or examples are inappropriately applied in unrelated contexts and amplifying downstream risk from any unsafe guidance the skill might contain.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This shell script creates a new directory and writes multiple files into it, which is a safety-relevant file modification operation for code files. While it logs that it is creating a CLI, it does not clearly disclose that it will generate and overwrite a set of project files in the target path.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The in-place sed command changes main.go after generation, which is a file modification action. Although expected for scaffolding, there is no explicit disclosure that the script performs in-place edits on generated files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.