ClawHub
Back to skill

Security audit

plydb

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent SQL-analysis guidance, but it can give an agent broad access to configured databases, files, cloud storage, and cached Google Sheets authorization with loose activation boundaries.

Review before installing. Use narrow config files, read-only database accounts, least-privilege cloud credentials, and avoid broad local paths or S3 globs unless needed. Treat cached Google OAuth as delegated account access: know where tokens are stored, how to revoke them, and confirm before letting the agent query private sheets or sensitive databases.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes generic terms like "sql", "query", "csv", "excel", and "database", which are common across many unrelated user requests. This can cause unintended invocation of the skill, exposing connected data sources or causing the agent to prefer this skill in contexts where the user did not intend database access or SQL execution.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal