ClawHub
Back to skill

Security audit

Evolve Self-Improving

Security checks for vulnerabilities and agentic risk

Overview

This skill persistently maintains a local knowledge folder for verified lessons, and its file access and validation behavior are disclosed and aligned with that purpose.

Install this only if you want the agent to maintain persistent local memory under ~/.agent-knowledge/. Review saved entries periodically because even scoped memory can influence future sessions; avoid allowing sensitive, private, credential, customer, or raw conversation content to be saved.

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
  • 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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill claims a constrained purpose—passively evaluating conversation learning signals and only saving under strict conditions—but its documented workflow includes broader filesystem inspection, index rebuilding, validation, and command-style operations not reflected in the declared purpose. This mismatch is dangerous because operators may authorize or trust the skill under a narrower mental model, while the actual behavior grants it broader access and modification capability over local knowledge files.

Content

No source excerpt is available for this finding.

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.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This Python file contains a natural-language module description entirely in Chinese, indicating a fixed language choice for the skill behavior/CLI description. The file does not offer any user opt-in or alternative locale, and no region-specific justification is documented here.

Content

No source excerpt is available for this finding.