ClawHub
Back to skill

Security audit

Curl

Security checks for vulnerabilities and agentic risk

Overview

This skill appears security-benign, but it mostly prints generic reference text rather than useful curl documentation.

Install only if you are comfortable with a low-capability reference skill whose curl content is very generic. Do not rely on it as an authoritative curl manual, and be aware that its name may be confusing because it is not the real curl command-line tool.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

There is no evidence of hidden or dangerous capabilities: the script only routes subcommands and prints static text, with no network access, file access, or external command execution beyond shell built-ins. However, the declared description says 'curl reference tool,' which implies documentation or reference material specifically about the curl utility. The actual content is largely generic placeholder-style guidance about 'devtools' concepts, installation, migration, performance, and security, with little to no real curl-specific commands, flags, examples, or accurate reference material. So while the high-level category of 'reference/help tool' is directionally similar, the implementation does not materially deliver the declared curl-focused purpose. This is a description-behavior mismatch based on primary purpose/accuracy, not on undeclared permissions or capabilities.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/script.sh (reported line 64)May include surrounding context.

sh
## Prerequisites
- Basic understanding of devtools concepts
- Required tools and access credentials
- System meeting minimum requirements

## Installation

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.