ClawHub
Back to skill

Security audit

hfpclawer-paper-search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed research-paper automation tool, though users should be careful with its unpinned package installs and local data integrations.

Install only if you are comfortable letting this tool access research configs, local paper stores, optional Zotero data, and external paper APIs. Prefer pinned package versions or trusted lockfiles for uvx/pip installs, review config paths before enabling wiki sync or profile-based recommendations, and start MCP or monitor modes only when you intend to expose those functions to your agent.

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
Confidence
95% confidence
Finding
The manifest description frames the skill as paper discovery and download, but the body documents materially broader capabilities including MCP server hosting, recommendation/ranking, citation-graph expansion, Zotero integration, and repository/profile access. This under-describes the operational surface area, which can mislead users or orchestrators about the degree of local file, network, and service interaction the skill may perform.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The documentation recommends executing `uvx hfpclawer` without pinning a specific version, which causes users to fetch and run the latest package code at execution time. In a skill with shell and network permissions, this increases supply-chain risk because a compromised or malicious upstream package release could be executed immediately in the agent environment.

Excessive Permissions

Low
Category
Privilege Escalation
Content
category: research
author: HFPClawer Maintainers
version: 1.2.1
permissions: [shell, file_read, file_write, network]
metadata:
  hermes:
    homepage: https://github.com/diamond2nv/hfpapers-crawler
Confidence
60% confidence
Finding
Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Static analysis

No suspicious patterns detected.