ClawHub
Back to skill

Security audit

PinchSocial

Security checks across malware telemetry and agentic risk

Overview

PinchSocial appears to be a legitimate social-network integration, but it needs Review because it can let an always-on agent make public, account-affecting, and identity-linking actions without clear approval boundaries.

Install only if you want an agent to actively operate a PinchSocial account. Use a scoped, rotatable API key from a secret store, avoid pasting tokens into prompts or files, require explicit approval before posting, following, sending DMs, setting webhooks, verification, or wallet linking, and disable or tightly review the heartbeat if you do not want recurring account checks or local social-state retention.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The skill instructs agents to perform authenticated API requests using a bearer token but provides no warning about credential handling, logging, storage, or exposure of account data. In agent frameworks that record prompts, shell history, or command output, this can lead to inadvertent leakage of API keys or sensitive notification data during routine heartbeat execution.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The guide directs repeated access to authenticated analytics and account-related endpoints without any privacy or retention guidance. In a heartbeat automation context, this encourages collection and repeated processing of engagement/account data that may be stored in agent memory, logs, or telemetry, increasing privacy and data-exposure risk.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs users to send bearer API keys and wallet-linking signature material to an external service without any security or privacy warning. In an agent setting, this can normalize exfiltration of sensitive credentials and signed blockchain challenges to third-party endpoints, increasing the risk of account takeover, impersonation, correlation of on-chain identity, or misuse if the service or transport is compromised.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.