ClawHub
Back to skill

Security audit

OPC Playbook

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown playbook for evaluating and building one-person AI startups, with no executable code or hidden high-risk behavior found.

Install this if you want Chinese-language structured guidance for evaluating and planning a one-person AI startup. Be aware it may activate on broad solo-founder or entrepreneurship topics and may default to Chinese unless you ask for another language.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
94% confidence
Finding

The trigger description includes broad startup-related terms such as '个人创业', '独立开发者创业', 'solo founder', and 'solo startup', which can cause the skill to activate in many general business discussions rather than only for narrowly scoped OPC evaluations. Over-broad activation can hijack unrelated conversations, inject unsolicited guidance, and increase the chance that users receive mismatched instructions or language/style constraints they did not ask for.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill content is written to operate in Chinese throughout, with no opt-in, locale negotiation, or fallback behavior for users who ask in another language. This can override user preferences, reduce comprehension, and in edge cases cause users to misunderstand strategic or operational advice, especially if the skill auto-activates due to broad triggers.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.