Security audit

Signup Lead

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently posts signup lead contact details to AgenticCreed and does not show hidden execution, persistence, or unrelated access.

Install only if you intend agents to create AgenticCreed signup leads. Before use, confirm the subject has consented to sharing their contact, address, birth date, phone, WhatsApp, job title, and joining-date details with AgenticCreed, and configure the API key only in environments allowed to submit those leads.

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: 95% confidence
Finding: The skill explicitly collects and transmits personally identifiable information, including email, name, address, date of birth, phone numbers, and employment-related data, to an external endpoint, but the description provides no privacy notice, consent guidance, retention information, or warning about third-party disclosure. This creates a real risk that users or calling agents will send sensitive personal data without informed consent or appropriate handling controls, increasing the chance of privacy violations, policy noncompliance, and unintended data disclosure.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The skill is designed to transmit sensitive personal data, including contact details, address, and date of birth, to an external endpoint, but the manifest does not indicate any requirement for explicit user consent, privacy notice, or regional data-handling controls. In an agent setting, this creates a meaningful risk of unauthorized sharing of personal information, especially if the skill is invoked implicitly or without clear disclosure.

Vague Triggers

Low

Confidence: 83% confidence
Finding: This is a manifest file, so vague-trigger review applies. The description explains what the skill does but does not define when it should or should not be invoked, nor does it limit activation to specific phrases or contexts, which could allow overly broad matching in systems that use manifest text for routing.

Static analysis

No suspicious patterns detected.