ClawHub

pixiv-skill

Security checks across malware telemetry and agentic risk

Overview

This Pixiv automation skill is mostly purpose-built, but it needs Review because it handles live account credentials and can change the user’s Pixiv account without clear safeguards.

Review before installing. Treat config.yaml as a secrets file, do not commit or share it, avoid untrusted proxies, and require explicit user approval before running like, follow, download, or monitor commands. There is no artifact-backed evidence of exfiltration or destructive behavior, but the credential handling and account-changing authority need careful user control.

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 (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The documentation instructs users to place a live Pixiv session cookie in config.yaml but provides no warning about its sensitivity, storage risks, rotation, scope, or accidental disclosure. In this skill context, the cookie grants authenticated access and potentially account-affecting actions like like/follow/download, so poor credential handling could lead to account compromise or unauthorized activity.

Missing User Warnings

Medium
Confidence
77% confidence
Finding
The script performs account-affecting actions (bookmark/public favorite and follow) immediately once invoked, with no confirmation, dry-run, or guardrail. In an agent or automation context, that increases the risk of unintended social actions being triggered by a prompt mistake, chaining bug, or malicious instruction, causing account abuse, reputational harm, or policy violations on the user's Pixiv account.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal