ClawHub
Back to skill

Security audit

Code Language Analyzer Claw

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently runs a local read-only script to count programming languages in a chosen project directory.

Install this if you want a local project language breakdown. Run it only on directories you intend to scan, especially in repositories that may contain private source code, because it reads source files to count lines.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · scripts/analyze_languages.py (reported line 105)May include surrounding context.

python
"node_modules", "bower_components",
    "vendor", "vendors",
    "__pycache__", ".pytest_cache", ".mypy_cache", ".ruff_cache",
    ".venv", "venv", "env", ".env",
    "dist", "build", "out", "target",
    ".next", ".nuxt", ".output",
    "coverage", ".nyc_output",

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill instructs the agent to inspect arbitrary project paths and run a local analysis script, but it does not declare any explicit tool scope such as allowed-tools or permissions. That creates an authorization gap where file-reading capability may be broader than intended, increasing the chance of over-reading sensitive files if the skill is auto-invoked or used on untrusted paths.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger description includes broad natural-language phrases like analyzing what languages a project uses or checking the tech stack, which can match many routine requests. Over-broad activation can cause the agent to invoke filesystem-scanning behavior unexpectedly, leading to unnecessary exposure of repository contents or user confusion about why a scan occurred.

Content

No source excerpt is available for this finding.