ClawHub
Back to skill

Security audit

determinability-checker

Security checks for vulnerabilities and agentic risk

Overview

This is a bounded local determinability checker with disclosed API authentication and no evidence of hidden execution, exfiltration, or persistence.

Before installing, review SECURITY.md, run the service only on 127.0.0.1 unless protected by a trusted proxy, keep JEP_CLIENTS and any trusted-key configuration out of source control, and grant only the check permission unless you knowingly use other documented security helpers.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared skill purpose is a bounded determinability check, but the underlying package reportedly also implements authentication, authorization, trusted-key verification, request hardening, and cryptographic signing behavior. This hidden or undocumented functionality materially expands the attack surface and can mislead reviewers into approving a skill with far broader security-sensitive behavior than advertised. Because the SKILL.md instructs users to provision authentication configuration while not disclosing these capabilities in the description or permissions, the mismatch is more dangerous, not less.

Content

No source excerpt is available for this finding.

Possible Typosquatting: 'uvicorn' resembles popular package 'gunicorn'

High
Category
Supply Chain
Confidence
70% confidence
Finding

Package name closely resembles a popular package, suggesting possible typosquatting. Attackers publish malicious packages with similar names to trick developers into installing them.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
78% confidence
Finding

The skill metadata declares no tool scope or explicit permissions even though the package reportedly has environment-variable access. Missing scope declarations weaken least-privilege controls and make it harder for operators to understand what sensitive resources the skill may read at runtime. In this context, the skill also references authentication configuration, which increases the chance that environment access includes secrets.

Content

No source excerpt is available for this finding.