ClawHub
Back to skill

Security audit

Founder Content

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only content-writing skill with some broad defaults, but it does not show hidden execution, persistence, or data theft.

Install this if you want an opinionated founder-content assistant. Before using it, be aware it may research public examples, inspect recent repo history for build-in-public drafts, and default Xiaohongshu output to Chinese unless you specify otherwise.

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 (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger description is extremely broad, including generic phrases like 'write a post', 'create content', and 'any content creation request'. In an agentic environment, this can cause unintended auto-invocation on ordinary user prompts, routing unrelated content tasks through this skill without explicit user consent and increasing the chance of unwanted external research behavior or platform-specific transformations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill states that 小红书 output should be 'Chinese-first' as part of the default rendering flow, without indicating that the user must request or approve the language change. This can override user expectations, produce outputs in an unintended language, and cause silent data transformation that is especially problematic when the user needs consistency across platforms or cannot validate the generated text.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The platform defaults table hard-codes language choices, including 'Chinese primary' for 小红书, which operationalizes a language override as a default behavior rather than an opt-in preference. In practice this can lead to unintended disclosures, mistranslations, or user confusion when the system reformats content into a language the user did not request.

Content

No source excerpt is available for this finding.