ClawHub
Back to skill

Security audit

Founder Content

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown content-writing skill with broad but disclosed content defaults and no executable code, persistence, credential handling, or posting authority.

Before installing, expect this skill to steer many content-writing requests into a founder/social-post workflow with platform-specific style and language defaults. Specify target platform, language, tone, and whether local git or PR context may be used, and review generated posts before publishing.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest description includes very broad activation phrases such as 'write a post', 'create content', and 'any content creation request', which can cause the skill to trigger on a wide range of unrelated user prompts. Overbroad routing increases the chance that this skill captures requests the user did not explicitly intend for it, leading to unwanted instruction injection into normal conversations and reduced user control over tool selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill states platform-specific output defaults, including language expectations, without clearly requiring the user's consent for those defaults. This can override user preferences or produce output in an unintended language/style, which is a safety and usability issue because it reduces transparency and may cause the assistant to act beyond the user's requested format.

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 languages by platform (for example English for Twitter/X and LinkedIn, Chinese primary for 小红书) without offering user choice. While not a code-execution risk, this can steer outputs into an unintended language or locale and creates hidden behavior that may conflict with the user's explicit or implicit preferences.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.