ClawHub
Back to skill

Security audit

Math Screenshot To Giscus

Security checks across malware telemetry and agentic risk

Overview

This skill is a focused formatting helper for math content and its limited file-writing guidance is disclosed and tied to that purpose.

Before installing, expect this skill to help transform math screenshots or pasted text into GitHub/giscus-ready Markdown. For complex formulas it may create a local output.md file, so choose or confirm the output path if preserving existing files matters. Only use GitHub API or live giscus verification with an account/token you are comfortable using for that test.

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

Medium
Confidence
90% confidence
Finding
The skill explicitly instructs the agent to write an output file into the working directory, but it does not require prior user consent or even a warning that the filesystem will be modified. In an agent setting, silent file creation is a side effect that can violate user expectations, overwrite artifacts, or be chained with other behaviors to persist data unexpectedly.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.