Privacy Cards

• Outcome: Review
• Latest audit: Sep 10, 2026 · 9:46 AM UTC
• Version: 1.0.0

Overview

This skill is coherent, but it gives agents direct instructions for sensitive payment-card actions without enough guardrails for card credentials or permanent closure.

Review this skill carefully before installing. It should only be used with a Privacy.com API key you intend to expose to the agent, preferably sandbox or least-privilege access. Avoid letting the agent print, log, save, or share full card numbers or CVVs, and require explicit confirmation before creating, changing limits, pausing, or permanently closing cards.

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

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (19)

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

```

**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`

All requests: `Authorization: api-key $PRIVACY_API_KEY`

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Create a Card

```bash
curl -s -X POST "https://api.privacy.com/v1/cards" \
  -H "Authorization: api-key $PRIVACY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

• Confidence: 60% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The documentation includes full payment card details in an example response, including PAN, CVV, and expiration date, without a strong warning not to expose, log, or display these values. In a skill whose purpose is card management, this increases the chance that downstream agents or users will mishandle highly sensitive financial data and leak usable card credentials.

External Transmission

Medium

• Category: Data Exfiltration

Content

### Pause a card
```bash
curl -s -X PATCH "https://api.privacy.com/v1/cards/{card_token}" \
  -H "Authorization: api-key $PRIVACY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"state": "PAUSED"}' | jq

• Confidence: 60% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

### Pause a card
```bash
curl -s -X PATCH "https://api.privacy.com/v1/cards/{card_token}" \
  -H "Authorization: api-key $PRIVACY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"state": "PAUSED"}' | jq

• Confidence: 60% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

### Pause a card
```bash
curl -s -X PATCH "https://api.privacy.com/v1/cards/{card_token}" \
  -H "Authorization: api-key $PRIVACY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"state": "PAUSED"}' | jq

• Confidence: 60% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill documents permanent card closure with no explicit warning that the action is irreversible and can disrupt legitimate payments. In an agent setting, omission of a confirmation or user-impact warning can cause accidental destructive actions against live financial instruments.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The documentation explicitly lists highly sensitive payment card fields (`pan`, `cvv`, `exp_month`, `exp_year`) but provides no warning that these values are PCI-sensitive, access-restricted, and must not be logged, displayed, persisted, or exposed to downstream tools. In a skill designed to create and manage virtual cards, this omission increases the chance that an agent or integrator will mishandle full card data, causing PCI compliance violations or credential theft if logs or outputs are exposed.

Missing User Warnings

Low

• Confidence: 85% confidence
• Finding: The update parameter documentation states that CLOSED is permanent, which indicates an irreversible action, but it does not provide any user-facing warning or caution about the destructive effect. For markdown skill documentation, irreversible operations should be accompanied by a clear warning about impact to user data or system state.

Static analysis

No suspicious patterns detected.