Security audit
Security checks for vulnerabilities and agentic risk
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.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**Environments:**
- Production: `https://api.privacy.com/v1`
- Sandbox: `https://sandbox.privacy.com/v1`
All requests: `Authorization: api-key $PRIVACY_API_KEY`
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -s -X POST "https://api.privacy.com/v1/cards" \
-H "Authorization: api-key $PRIVACY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
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.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
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
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
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
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
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
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.
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.
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.
No suspicious patterns detected.