ClawHub
Back to skill

Security audit

project-analyzer

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward project-analysis skill whose file inspection and read-only counting commands fit its stated purpose.

Install this only for repositories you are comfortable letting an agent inspect. The skill is analysis-oriented, but users should keep any shell usage limited to read-only discovery and counting commands like those documented.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The manifest and documentation present the skill as a codebase analysis agent using Glob, Read, and Grep to inspect an existing project. Line L152 additionally authorizes Bash usage (wc -l, find), which introduces command-execution capability that is not clearly justified by the stated analysis-only purpose and expands the operational surface beyond straightforward code inspection tools.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.