ClawHub
Back to skill

Security audit

yu

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward citation and PDF reference checker, with the main caution that research details may be checked against external academic databases.

Use this skill for ordinary citation checking and literature review work. Avoid uploading confidential, unpublished, or proprietary manuscripts unless you are comfortable with citation metadata and document-derived text being processed during external academic database verification.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly supports PDF upload, PDF text/reference matching, and live verification against external academic databases, but it does not disclose that user-provided document contents, citation lists, and extracted metadata may be transmitted to third-party services or otherwise processed outside the local environment. In a research context, uploaded PDFs may contain unpublished manuscripts, sensitive data, or proprietary drafts, so the lack of a clear data-handling and consent notice creates a real privacy and confidentiality risk.

Content

No source excerpt is available for this finding.

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
80% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

md
结构化输出表格

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The natural-language description says triggers are supported in Chinese and English only. Under the policy, language constraints should either provide user choice or be clearly justified as region- or domain-specific; this limitation is not explicitly justified here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.