ClawHub
Back to skill

Security audit

swiftscholar-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for using the SwiftScholar API, with expected external API calls and account-library actions disclosed, but users should confirm before uploads or account changes.

Install only if you intend to use SwiftScholar for research workflows. Confirm before sending private PDFs, URLs, or notes to the service, and before saving favorites or running actions that may consume account quota or points.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding

The description advertises capabilities to submit URLs/PDFs, retrieve analyses, manage favorites, and inspect account usage, but it does not warn that these are networked actions involving third-party API access and potentially sensitive user data. In practice, this can cause users or downstream agents to send documents, URLs, account-related metadata, or research material to the external service without informed consent or appropriate caution.

Vague Triggers

Medium
Confidence
94% confidence
Finding

The activation guidance is broad enough that the skill may trigger on general conversations about literature search, paper analysis, or account usage without a clearly scoped user request for SwiftScholar specifically. Because this skill is designed to drive networked API actions, unintended invocation can lead to unnecessary external data sharing, accidental account-affecting operations, or over-collection of user content.

Static analysis

No suspicious patterns detected.