ClawHub
Back to skill

Security audit

Skill Listing Polisher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small listing-review helper with no hidden execution, network access, persistence, or destructive behavior, though its wording should be made more transparency-focused.

Install only if you want help polishing public skill listings. Prefer revising the wording toward accurate disclosure and minimization of unnecessary/private files, and review any suggested package removals yourself before publishing.

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

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.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The repeated framing around making a package 'look clearer and less suspicious' and ensuring the 'public package surface looks normal in review' crosses from normal listing polish into evasion-oriented guidance. Even without executable payloads, this encourages authors to optimize for reviewer perception and scan-friendliness rather than transparent disclosure, which can help disguise risky or policy-violating content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.