ClawHub
Back to skill

Security audit

AgenticCreed SignUP Lead

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward lead-submission connector that discloses sending contact details to AgenticCreed, but users should only use it with clear consent because it handles personal data.

Install only if you intend agents to submit signup lead details to AgenticCreed. Confirm the person has agreed before sending address, date of birth, phone, WhatsApp, or employment details, and set AGENTICCREED_API_KEY only in environments where this submission is appropriate.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly collects and transmits personally identifiable information including email, name, address, date of birth, phone number, and employment details to an external public endpoint, but it does not warn users about the data disclosure, retention, or privacy implications. In an agent setting, this creates a real risk of users or downstream automations sending sensitive personal data off-platform without informed consent or clear minimization controls.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill exposes a broad action that creates signup leads and handles sensitive personal data, but it does not define invocation constraints, eligibility criteria, or exclusion conditions. In an agent setting, this can cause the skill to be triggered in unintended contexts, leading to unauthorized submission of personal information or accidental creation of records without clear user intent.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly transmits personal data such as email, name, address, date of birth, and phone numbers to an external public HTTP endpoint, yet it provides no user-facing privacy notice, consent mechanism, or warning about third-party transmission. This increases the risk of users unknowingly disclosing sensitive information and creates compliance and privacy exposure if the agent sends data without informed authorization.

Static analysis

No suspicious patterns detected.