Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only API design skill whose examples are consistent with its stated purpose and do not show hidden execution, exfiltration, or persistence.
Installers should treat this as a documentation-oriented API design aid. Review any generated API specs before using them, especially endpoints that delete or modify resources, but the skill itself does not perform those actions.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
{
"error": {
"code": "INVALID_TOKEN",
"message": "The access token is invalid or has expired",
"details": {
"reason": "token_expired",
"expired_at": "2024-01-15T10:00:00Z"
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
{
"error": {
"code": "INVALID_TOKEN",
"message": "The access token is invalid or has expired",
"details": {
"reason": "token_expired",
"expired_at": "2024-01-15T10:00:00Z"
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
POST /users # Create resource PUT /users/{id} # Replace resource PATCH /users/{id} # Update resource DELETE /users/{id} # Delete resource
**Bad Resource URIs:**
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
DELETE - Remove Resource
DELETE /users/123
Response: 204 No Content
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
DELETE - Remove Resource
DELETE /users/123
Response: 204 No Content
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
5. **Maintain old versions** - Support at least 2 versions simultaneously
6. **Document changes** - Provide detailed migration guides
7. **Use semantic versioning** - For internal/SDK versioning
8. **Never break without warning** - Always announce breaking changes
9. **Provide tools** - Migration scripts, updated SDKs
10. **Monitor usage** - Track which versions are being used
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
5. **Maintain old versions** - Support at least 2 versions simultaneously
6. **Document changes** - Provide detailed migration guides
7. **Use semantic versioning** - For internal/SDK versioning
8. **Never break without warning** - Always announce breaking changes
9. **Provide tools** - Migration scripts, updated SDKs
10. **Monitor usage** - Track which versions are being used
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content-Type: application/problem+json
{
"type": "https://api.example.com/errors/resource-not-found",
"title": "Resource Not Found",
"status": 404,
"detail": "User with ID 123 does not exist",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content-Type: application/problem+json
{
"type": "https://api.example.com/errors/resource-not-found",
"title": "Resource Not Found",
"status": 404,
"detail": "User with ID 123 does not exist",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content-Type: application/problem+json
{
"type": "https://api.example.com/errors/resource-not-found",
"title": "Resource Not Found",
"status": 404,
"detail": "User with ID 123 does not exist",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content-Type: application/problem+json
{
"type": "https://api.example.com/errors/resource-not-found",
"title": "Resource Not Found",
"status": 404,
"detail": "User with ID 123 does not exist",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content-Type: application/problem+json
{
"type": "https://api.example.com/errors/resource-not-found",
"title": "Resource Not Found",
"status": 404,
"detail": "User with ID 123 does not exist",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content-Type: application/problem+json
{
"type": "https://api.example.com/errors/resource-not-found",
"title": "Resource Not Found",
"status": 404,
"detail": "User with ID 123 does not exist",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content-Type: application/problem+json
{
"type": "https://api.example.com/errors/resource-not-found",
"title": "Resource Not Found",
"status": 404,
"detail": "User with ID 123 does not exist",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content-Type: application/problem+json
{
"type": "https://api.example.com/errors/resource-not-found",
"title": "Resource Not Found",
"status": 404,
"detail": "User with ID 123 does not exist",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content-Type: application/problem+json
{
"type": "https://api.example.com/errors/resource-not-found",
"title": "Resource Not Found",
"status": 404,
"detail": "User with ID 123 does not exist",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content-Type: application/problem+json
{
"type": "https://api.example.com/errors/resource-not-found",
"title": "Resource Not Found",
"status": 404,
"detail": "User with ID 123 does not exist",
No suspicious patterns detected.