ClawHub
Back to skill

Security audit

Opc Project Screener

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language guided checklist for evaluating one-person-company startup projects and does not request risky system access or hidden authority.

This looks safe to install for Chinese-language OPC or early startup screening. Users should be aware it may activate for broader startup feasibility requests and should treat its business conclusions as advisory, not as financial or investment advice.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The activation description includes broad phrases such as '项目可行性判断' and '初创项目筛选', which can match generic startup or project-evaluation requests outside the intended OPC niche. This can cause overbroad skill invocation, leading the agent to apply specialized OPC screening behavior in unrelated contexts and produce misleading or lower-quality guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill is written entirely in Chinese without declaring a locale restriction or fallback language behavior. In multilingual environments, this can cause misrouting, user misunderstanding, or partial compliance with instructions when the invoking user or orchestrator expects another language, reducing reliability and potentially causing incorrect assessments.

Content

No source excerpt is available for this finding.