ClawHub
Back to skill

Security audit

ragret-search

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its stated RAGret search purpose, but it needs review because it can send an API key and sensitive queries to an unvalidated or plaintext endpoint.

Install only if you trust the RAGret endpoint you will configure. Prefer HTTPS for any non-local service, confirm the base URL before first use, use a least-privilege API key, and avoid sending confidential queries to unknown or plaintext endpoints.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:21
Finding

API Credentials and Sensitive Queries May Be Sent over Plaintext HTTP

Content
View full analysis
Remediation
View remediation

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
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description uses broad activation criteria such as generic search, retrieval, or knowledge-base intent, which could cause the skill to trigger for many user requests that were not clearly intended for this specific remote service. Because the skill directs the agent to contact a remote API and even suggests defaulting to a localhost endpoint when the base URL is unclear, overbroad activation increases the chance of unintended network access, data disclosure to an internal service, or workflow hijacking away from safer/local retrieval paths.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.