ClawHub
Back to skill

Security audit

Cross Platform Repurposing

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only content repurposing skill whose behavior is disclosed and aligned with turning source content into platform-native posts.

Before installing, confirm that you want agents to use your brand-profile and voice context for social content drafts, and review any generated posts before approving scheduling or publication.

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
92% confidence
Finding

The trigger phrase 'or wants to fan content out' is overly broad and can cause the skill to activate for loosely related requests rather than explicit repurposing intent. In an agentic system, ambiguous activation increases the chance of incorrect tool selection, unintended access to brand/voice context, and accidental downstream scheduling or content transformation actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

Lines L04-L05 instruct that output must use a fixed "blunt indie-founder" voice from voice.md. This is a natural-language style constraint imposed unconditionally, with no indication that the user can choose or opt into another language/locale or style.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.