Back to skill

Security audit

keevx-image-to-video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Keevx image-to-video API guide; it sends user-selected images and prompts to Keevx as part of its stated purpose.

Install only if you are comfortable sending selected images, prompts, and generated-media requests to Keevx using your Keevx API key. Keep the key in an environment variable or secrets manager, do not hardcode or share it, and avoid uploading sensitive, private, proprietary, or unauthorized images unless Keevx's handling and retention terms are acceptable for your use.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (8)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

md
## API Endpoints

- Base URL: `https://api.keevx.com/v1`
- Upload image: `POST /figure-resource/upload/file` (Content-Type: `multipart/form-data`)
- Create task: `POST /image_to_video` (Content-Type: `application/json`)
- Query status: `GET /image_to_video/{task_id}`

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 116)May include surrounding context.

md
## API Endpoints

- Base URL: `https://api.keevx.com/v1`
- Upload image: `POST /figure-resource/upload/file` (Content-Type: `multipart/form-data`)
- Create task: `POST /image_to_video` (Content-Type: `application/json`)
- Query status: `GET /image_to_video/{task_id}`

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 134)May include surrounding context.

md
## API Endpoints

- Base URL: `https://api.keevx.com/v1`
- Upload image: `POST /figure-resource/upload/file` (Content-Type: `multipart/form-data`)
- Create task: `POST /image_to_video` (Content-Type: `application/json`)
- Query status: `GET /image_to_video/{task_id}`

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 156)May include surrounding context.

md
## API Endpoints

- Base URL: `https://api.keevx.com/v1`
- Upload image: `POST /figure-resource/upload/file` (Content-Type: `multipart/form-data`)
- Create task: `POST /image_to_video` (Content-Type: `application/json`)
- Query status: `GET /image_to_video/{task_id}`

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs users to upload local image files to a third-party service and then use the returned hosted URLs, but it does not explicitly warn that local files leave the user's environment and may be stored externally. This creates a real privacy and data-handling risk, especially if users provide sensitive or proprietary images assuming only local processing.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This finding duplicates the upload example at line 88 and represents the same real risk: a local image is transmitted to a third-party endpoint for hosting/processing. In context, the transmission is part of the advertised feature, but the danger remains because users may not realize the data leaves local control.

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

Upload Local File

bash
curl --location 'https://api.keevx.com/v1/figure-resource/upload/file' \
  --header 'Authorization: Bearer $KEEVX_API_KEY' \
  --header 'source: skill' \
  --form 'file=@"/path/to/local/image.png"'

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This finding duplicates the upload example at line 88 and represents the same real risk: a local image is transmitted to a third-party endpoint for hosting/processing. In context, the transmission is part of the advertised feature, but the danger remains because users may not realize the data leaves local control.

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

Upload Local File

bash
curl --location 'https://api.keevx.com/v1/figure-resource/upload/file' \
  --header 'Authorization: Bearer $KEEVX_API_KEY' \
  --header 'source: skill' \
  --form 'file=@"/path/to/local/image.png"'

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill requires an API key and authenticated calls to an external service but provides no guidance on secure credential handling or the privacy implications of sending prompts, image URLs, and uploaded media to a third party. While this is common for API-based skills, omission of these warnings can lead to inadvertent key exposure or unsafe use with sensitive data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.