ClawHub
Back to skill

Security audit

Trendshift

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-oriented Trendshift connector wrapper with clear setup guidance and no hidden persistence or destructive behavior.

Before installing, be aware that this skill depends on OOMOL's oo CLI and a connected Trendshift account. Review the CLI install script and only complete login or connection steps when you intend to use OOMOL as the credential-handling intermediary for Trendshift data reads.

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
90% confidence
Finding
The description says to use this skill for "ANY Trendshift request" and "instead of calling the API directly," which is an overly broad routing instruction. While the skill only exposes read-oriented Trendshift connector actions in this file, such blanket activation can cause the agent to invoke the skill in situations where a narrower tool choice, user confirmation, or direct review of alternatives would be more appropriate.

Static analysis

No suspicious patterns detected.