Helena AI Marketing Agent

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 11:30 AM UTC
• Version: 1.0.0

Overview

This skill coherently connects to Helena for user-authorized marketing work and includes clear safeguards for credentials and live campaign actions.

Install only if you intend to connect your Enrich Labs account and let Helena operate on brand marketing data. Review Helena's own permissions and connected platforms, and only authorize publishing, spending, contact, campaign-change, or deletion actions when you mean to perform them.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Credential Access

High

• Category: Privilege Escalation
• Confidence: 70% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

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

text

3. If `helena` already points somewhere else, do not overwrite it without explicit confirmation. If it has the correct URL but needs authorization, run `openclaw mcp login helena`.
4. Never ask the user to paste an Enrich Labs password, OAuth code, access token, or refresh token into chat. Let the browser flow handle credentials. In a headless environment, follow the safe `--code` fallback printed by OpenClaw.
5. Verify the connection with `openclaw mcp doctor helena --probe`. If the tool is not available in the current conversation afterward, ask the user to start a new conversation or restart their OpenClaw gateway.

If Enrich Labs reports that MCP access is unavailable for the selected brand, explain the account or plan requirement and direct the user to <https://enrichlabs.ai/mcp>. Do not retry in a loop.

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 80% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

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

text

3. If `helena` already points somewhere else, do not overwrite it without explicit confirmation. If it has the correct URL but needs authorization, run `openclaw mcp login helena`.
4. Never ask the user to paste an Enrich Labs password, OAuth code, access token, or refresh token into chat. Let the browser flow handle credentials. In a headless environment, follow the safe `--code` fallback printed by OpenClaw.
5. Verify the connection with `openclaw mcp doctor helena --probe`. If the tool is not available in the current conversation afterward, ask the user to start a new conversation or restart their OpenClaw gateway.

If Enrich Labs reports that MCP access is unavailable for the selected brand, explain the account or plan requirement and direct the user to <https://enrichlabs.ai/mcp>. Do not retry in a loop.

Static analysis

No suspicious patterns detected.