ClawHub
Back to skill

Security audit

Longform Blog Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward writing assistant skill with no executable code, persistence, credential access, or hidden data flows.

Installers should expect this skill to shape longform article drafting and sometimes call a companion concept-decoder skill for complex concepts. Users should still verify factual claims and citations before publishing, especially for current research or fast-changing technical topics.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README frames the skill as bilingual Chinese/English and presents all primary instructions in those two languages without an explicit mechanism to honor the user's preferred language. This can override user expectations or downstream agent defaults, causing unwanted language switching, reduced usability, and potential prompt-control conflicts in multi-skill environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.