ClawHub

Precoro

Security checks across malware telemetry and agentic risk

Overview

This Precoro skill appears purpose-built for a real integration, but it should be reviewed because it can run authenticated actions and raw API requests against sensitive procurement records without clear safety limits.

Review before installing. Use a least-privilege Membrane/Precoro connection, keep human approval for purchases, payments, approvals, user or role changes, and destructive edits, and use the skill only for clearly Precoro-directed tasks.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description says to use the integration whenever the user wants to interact with Precoro data, which is broad enough to trigger on many ordinary procurement, finance, or records-related requests without clearly requiring explicit user intent or confirmation. In a skill that can execute actions and proxy live API requests, over-broad routing increases the chance of unintended access, reads, or modifications to business data.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documents running arbitrary actions and direct proxy requests against the Precoro API but does not warn that these commands may read, create, update, or delete live procurement and financial records. Because the integration targets real business systems and supports authenticated execution, omission of safety boundaries can lead an agent to perform destructive or privacy-impacting operations without adequate user confirmation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal