ClawHub
Back to skill

Security audit

hfpclawer-paper-search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed research-paper search and organization tool, with some broad optional integrations users should review before enabling.

Before installing, review whether you want the optional Zotero read/write paths, MCP server registration, local profile use, and monitor daemon. Keep private profiles and Zotero identifiers in local gitignored files, and prefer pinned package versions for repeatable installs.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest describes a paper discovery/download/organization pipeline across arXiv, HuggingFace Papers, and OpenReview with optional wiki sync. This file documents substantially broader behavior: recommendation and learned re-ranking, repo/user profile ingestion, citation-graph expansion, Zotero read/write/ingest, and running an MCP server for agent tool exposure. Those are not obvious implementation details of the stated narrow pipeline and materially broaden the skill's functional scope.

Content

No source excerpt is available for this finding.

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
60% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · SKILL.md (reported line 10)May include surrounding context.

md
category: research
author: HFPClawer Maintainers
version: 1.2.2
permissions: [shell, file_read, file_write, network]
metadata:
  hermes:
    homepage: https://github.com/diamond2nv/hfpapers-crawler

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest says the skill discovers papers from arXiv, HuggingFace Papers, and OpenReview. The documentation states support for additional sources and verification services, including PapersWithCode and several biomedical and metadata providers, which broadens the external systems the skill interacts with beyond the manifest's stated scope.

Content

No source excerpt is available for this finding.