ClawHub
Back to skill

Security audit

meta-analysis-journal-selector

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed academic journal-selection helper with local reference data and no executable or persistence behavior.

Before installing, treat the journal metrics and acceptance-rate estimates as decision support, not authoritative submission advice. Verify current journal data and requirements on publisher or indexing sites, especially because the packaged reference paths appear inconsistent with the SKILL.md instructions.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes very broad phrases such as 'help me select a journal' and 'find journals that accept meta-analyses', which can match common user requests outside the narrow intended context. Overbroad activation can cause the wrong skill to intercept conversations, leading to irrelevant guidance, unintended access to internal reference data, or bypass of safer/more appropriate routing logic.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This CSV contains natural-language values in Chinese such as "医学", "社会学", "生物学", "心理学", "教育学", and "是/否" across the dataset while other fields are in English. Because the file provides no indication that Chinese output is required, optional, or region-specific, it implicitly enforces a mixed locale without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.