ClawHub
Back to skill

Security audit

is-it-true

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed critical-thinking and fact-checking guide, with no evidence of hidden execution, exfiltration, persistence, or destructive behavior.

Install only if you want an agent to apply a structured critical-thinking and fact-checking workflow. Because it encourages web and multi-source searches, do not use it on private or confidential claims unless you are comfortable with the agent using that content for verification queries.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared purpose describes an end-user analytical reasoning skill focused on evaluating claims and arguments. The supplied code does not implement any critical-thinking, content analysis, fact-checking, or web analysis behavior. Instead, it performs local file validation and packaging for skill distribution. This is a materially different primary purpose and includes undeclared filesystem/archive manipulation capabilities unrelated to the declared description.

Content

No source excerpt is available for this finding.

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
---
AIGC:
    ContentProducer: Minimax Agent AI
    ContentPropagator: Minimax Agent AI
    Label: AIGC
    ProduceID: bc203e0cd506d5a9ca68357cf773d010
    PropagateID: bc203e0cd506d5a9ca68357cf773d010
    ReservedCode1: 30440220540d3f58319068646b7214325de7a1afa68ed12a2eb91223e55452ba6d28b652022024fb2c261d27f9224890637aa90f255cc65293332b2620d4c4d4502098849fe9
    ReservedCode2: 30460221008d52cba1d41b13b2708c6333d89597deffd67670f7d4124f4913ca8f2725b556022100e58a2bd576c0a1ba00408a9dd98c611a9e4972674e7b1c4e3576710470d1c2f7
description: Conduct critical analysis of viewpoints, factual statements, or web content using the critical thinking framework from "Asking the Right Questions". Use when users ask to verify information authenticity, examine viewpoint logic, analyze argument validity, distinguish facts from opi

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.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation criteria are broad and everyday—such as verifying information authenticity, examining logic, or analyzing web content—which can cause over-invocation on loosely related prompts. In agent environments, ambiguous triggering expands the skill’s operational surface and can route sensitive or adversarial content into workflows not intended by the user or system designer.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.