ClawHub
Back to skill

Security audit

Academic Writing Custom

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward academic-writing helper with strict citation and formatting guidance, and I found no commands, credential handling, persistence, or hidden behavior.

Install this if you want academic-style writing and citation discipline. Be aware it may apply a rigid Markdown and citation format when activated, and users should still verify citations and suitability for non-academic contexts.

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)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill description is broad and lacks clear activation boundaries, exclusions, or negative examples, so it may be invoked for loosely related writing tasks beyond intended academic-use scenarios. In an agent setting, ambiguous scope can cause over-application of the skill’s strong formatting and citation rules, increasing the chance of inappropriate behavior, unreliable routing, or misuse in contexts where stricter safeguards should apply.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.