ClawHub
Back to skill

Security audit

Anthropic Founder Handbook

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language entrepreneurship advice skill with broad activation wording, but it does not request system access, credentials, persistence, or hidden execution.

Install this if you want a Chinese-language startup coaching handbook. Be aware that its trigger wording is broad, so it may be invoked for many entrepreneurship discussions, and it does not provide multilingual alternatives.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill declaration is overly broad and explicitly says it must be used for a wide range of common entrepreneurship topics. This can cause the agent to invoke the skill in situations where it is only partially relevant, crowding out more appropriate instructions and creating prompt-scope hijacking behavior. In context, the content is non-code and not overtly malicious, which lowers severity, but the mandatory broad activation still meaningfully increases the chance of inappropriate routing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description is written to force a specific language behavior without obtaining user preference or consent. This can degrade usability, override system/user language expectations, and in multi-skill settings may act as an instruction-level conflict that pushes the assistant into an unintended response mode. The surrounding skill is advisory rather than operational, so the impact is limited, but it is still an instruction-quality and control issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains instructional content exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into another language. Under the language/locale policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all instructions in Chinese only, with no indication that the user can choose another language or that the content is intentionally limited to a Chinese-speaking context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The entire skill content is written in Chinese and does not offer any language choice, opt-in, or note that it is intended for a specific locale. Under the policy rule, forcing a specific language without user selection is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.