ClawHub
Back to skill

Security audit

Feedier

Security checks for vulnerabilities and agentic risk

Overview

This Feedier skill is a coherent OOMOL connector wrapper with disclosed write/delete capability and explicit confirmation requirements.

Install only if you want your agent to manage Feedier reports through OOMOL. Review write and delete requests carefully, especially report deletions and share-link creation, and only approve payloads and targets you recognize.

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
96% confidence
Finding
The description says to use this skill for ANY Feedier request and instead of calling the API directly, which is an overly broad invocation trigger. This can cause the agent to route unrelated or higher-risk Feedier tasks through the skill automatically, increasing the chance of unintended data access or state-changing operations being initiated with insufficient user intent validation.

Static analysis

No suspicious patterns detected.