ClawHub
Back to skill

Security audit

Get Biji

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Get Biji connector that can read and change notes, with explicit confirmation requirements for writes and deletions.

Install this only if you want the agent to operate your Get Biji account through OOMOL. Read-only actions can inspect account notes and knowledge bases; writes, sharing, updates, and deletions should be allowed only after you confirm the exact target and payload.

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
84% confidence
Finding
The skill description uses sweeping routing language like 'Use this skill for ANY Get Biji request' and 'instead of calling the API directly,' which can cause an agent to invoke this skill whenever Get Biji is mentioned, even when a narrower or safer workflow would be more appropriate. In a skill that includes write and destructive actions, overly broad invocation boundaries increase the chance of unintended state-changing operations, especially if an upstream planner does not strictly separate read-only from mutating intents.

Static analysis

No suspicious patterns detected.