ClawHub
Back to skill

Security audit

Paper Reading Socratic Coach

Security checks across malware telemetry and agentic risk

Overview

This is a text-only academic coaching skill whose state-file behavior is disclosed and aligned with its learning purpose, though users should treat those saved records as private study data.

Safe to install for paper-reading coaching. Before using it in a shared or synced workspace, decide whether you want persistent learning records saved under `.paper-reading-coach/`; avoid storing confidential papers or sensitive personal notes there unless that workspace is private.

SkillSpector

By NVIDIA
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 (1)

Missing User Warnings

Low
Confidence
92% confidence
Finding
The README states that if the agent can write files, it should automatically update workspace-level learning-state files, but it does not clearly warn users that these records may contain sensitive study history, research interests, or performance weaknesses. This creates a real privacy risk because users may not realize persistent data is being stored across sessions, especially in shared or synced workspaces.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.