ClawHub
Back to skill

Security audit

Skill Scanner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed security checklist for package and skill installs, with no executable payload or hidden persistence.

Install only if you want an agent to pause and perform security checks before package, plugin, or skill installs. Treat its output as a checklist, and avoid letting it read secret file contents unless you have explicitly approved that deeper inspection.

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
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says the skill is triggered by any install, add, or package addition request, which is broader than the narrowly defined security-review use case. Overly broad activation can cause the skill to intercept unrelated package-management workflows, increasing the chance of unnecessary invocation and security-review bypass or confusion in multi-skill environments.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
- Flag packages with 50+ transitive dependencies

### 4. Lifecycle Scripts (HIGH RISK)
- Check for `preinstall`, `install`, `postinstall` scripts — these run arbitrary code
- `npm info <package> scripts` or inspect `package.json`
- pnpm blocks these by default; npm does NOT
- If lifecycle scripts exist, flag it explicitly to the user

Static analysis

No suspicious patterns detected.