ClawHub
Back to skill

Security audit

Hypertxt Content Operations

Security checks across malware telemetry and agentic risk

Overview

This skill gives an agent structured instructions for using Hypertxt content tools and requires explicit approval before spending credits, changing article state, syncing GSC, or publishing.

Install only if you intend to let the agent operate your Hypertxt account through the MCP server. Keep the API key in secret configuration, verify the selected project, destination, and mode before approving actions, and treat generation, sync, state changes, and publishing as real account-impacting operations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (1)

Scope Creep

Low
Category
Excessive Agency
Content
furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
Confidence
70% confidence
Finding
NOT LIMITED TO

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.