Back to skill

Security audit

broken-link-checker

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report that crafted links in scanned documentation can trigger shell commands, creating a serious security weakness beyond its link-checking purpose.

Treat installation as risky, especially where the skill may scan untrusted documentation or run with access to sensitive files or secrets. Consider waiting for a reviewed fix and clarified tool scope; the scan was partial, so its evidence is incomplete.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
index.js
Finding

Documentation URLs are interpreted as shell commands

Content
View full analysis

Impact

An attacker-controlled documentation link can execute arbitrary commands as the reviewing agent or CI runner, enabling access to available secrets and modification of accessible files.

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The normal scanning and curl requests match the description. The material exception is checkUrl(), which passes an interpolated URL to execSync(). Double quotes do not prevent shell command substitution using backticks or $(), and the URL extraction and HTTP(S) prefix checks do not adequately sanitize shell syntax. Consequently, scanning untrusted documentation can execute commands with the scanner's privileges, exceeding the declared link-checking behavior. This is an injection vulnerability, not evidence of an intentionally malicious payload.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: shell.

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.