ClawHub
Back to skill

Security audit

PostgreSQL

Security checks across malware telemetry and agentic risk

Overview

This is a coherent PostgreSQL operations skill with disclosed local preference storage and safety-oriented database guidance, though users should be mindful of logging and saved memory.

Before installing, understand that the skill may remember PostgreSQL preferences and context in ~/Clawic/data/pg/ and may use general profile settings. Review generated SQL before running it on production, use least-privileged database credentials, and avoid enabling statement logging in ways that capture secrets or personal data without retention and access controls.

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 (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The logging example states that slow statements are logged "with parameters" but does not warn that PostgreSQL logs may therefore capture secrets or sensitive personal data embedded in SQL literals. In a PostgreSQL operations skill, readers may copy this configuration directly into production, increasing the chance of credential, token, or PII exposure through centralized logs and downstream log processors.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly instructs the agent to read from and later write to user-specific files under `~/Clawic/data/pg/` and `~/Clawic/profile.yaml` without requiring any user notification, consent, or per-action confirmation. This creates a privacy and integrity risk because the agent may silently collect persistent context from local files and modify stored preferences based on conversational content, which can surprise users and persist unintended or sensitive data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.