ClawHub
Back to skill

Security audit

Citation Verifier

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow citation-checking helper with no executable code, persistence, or hidden behavior.

Install this if you want an agent helper for checking individual citations or identifiers. Use it for DOI, arXiv, PubMed, URL, or specific citation checks, not for broad literature searches or paper recommendations.

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

Medium
Confidence
88% confidence
Finding
The description says to use the skill when the user pastes a DOI, URL, citation string, or 'paper title and wants it checked.' The phrase 'wants it checked' is broad and the inclusion of a plain paper title overlaps with common requests that might instead be literature search, fact-checking, or summarization, without clear exclusion boundaries in the trigger description.

Static analysis

No suspicious patterns detected.