ClawHub
Back to skill

Security audit

Prospeo

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Prospeo connector that uses OOMOL's `oo` CLI for disclosed Prospeo searches and enrichment, with no evidence of hidden or destructive behavior.

Install this if you want your agent to query Prospeo through OOMOL-managed credentials. Be aware that search and enrichment payloads are sent to the Prospeo connector and may use Prospeo/OOMOL account credits; use care with sensitive people or company lookups.

SkillSpector

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
91% confidence
Finding
The description directs the agent to use this skill for ANY Prospeo-related request, which is an overly broad trigger condition. Broad routing can cause the agent to invoke this skill in contexts where Prospeo access is unnecessary or where user intent is ambiguous, increasing the chance of unintended data access, external data disclosure, or bypass of more context-appropriate safeguards.

Static analysis

No suspicious patterns detected.