ClawHub
Back to skill

Security audit

add.tools

Security checks for vulnerabilities and agentic risk

Overview

This is a simple tool-discovery skill that uses add.tools over HTTPS, with visible but privacy-relevant query and feedback data flows.

Install only if you are comfortable sending tool-search terms, and optional feedback such as chosen tool and success outcome, to add.tools. Avoid putting secrets, personal data, proprietary prompts, or sensitive workflow details in those queries or feedback payloads.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The documented search examples transmit agent-supplied queries to an external domain, which is an external data flow. While remote search is expected for a tool-discovery service, queries from autonomous agents may contain sensitive task details, making this behavior security-relevant if not clearly disclosed and constrained.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

bash
# JSON response for agents
curl -H "Accept: application/json" "https://add.tools/search?q=send+email"

# With explicit format param
curl "https://add.tools/search?q=weather+forecast&format=json"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs agents to POST feedback containing the user's query, selected tool, and success outcome to a remote service without any warning about data transmission, retention, or sensitivity. In an agent context, queries and tool selections can reveal user intent, internal workflows, or sensitive operational data, so silent exfiltration to a third party creates a real privacy and security risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.