ClawHub

PingCode

Security checks across malware telemetry and agentic risk

Overview

This PingCode skill matches its stated project-management purpose, but it can change live work items and handles API secrets in a way users should review carefully.

Install only if you trust the publisher and can create a narrowly scoped PingCode application. Treat the update script as live-write access: verify exact work-item IDs before running it, avoid automated execution without user approval, and rotate credentials if secrets or token URLs appear in terminal, agent, proxy, or request logs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill documents commands that modify remote work items, including assignee, dates, priority, and status, without any warning, confirmation, or clear indication that these are state-changing actions against a live project management system. In an enterprise context, accidental execution could alter project records, disrupt workflows, or create audit and integrity issues across a team.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation includes a token request that transmits both client_id and client_secret directly in the URL query string and shows a live-looking access token value, but provides no warning about secret handling, redaction, logging exposure, or secure storage. In an agent skill context, this can encourage unsafe implementation patterns where secrets are embedded in requests, captured in logs, browser history, proxies, or analytics systems, increasing the chance of credential leakage.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal