Back to skill

Security audit

p-image-edit

Security checks across malware telemetry and agentic risk

Overview

This photo-editing skill is mostly coherent, but it asks the agent to install multiple external skills and upload user images to Pruna's API.

Install only if you are comfortable letting the agent add Pruna companion skills from external package references and sending the photos you provide to Pruna's API. Avoid using sensitive personal, biometric, confidential, or proprietary images unless you have permission to share them with that service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (23)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The description says to use the skill when someone wants to edit an existing photo, including broad phrases like changing backgrounds or applying prompt-driven edits. Without clearer boundaries or negative examples in the trigger description itself, this could overlap with many common image requests and lead to ambiguous invocation between adjacent image skills.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs the agent to install and run external skill packages via `npx skills add ...` without pinning an immutable version or digest for the `npx skills` tool itself. This creates a supply-chain risk: a future compromised or changed package/tool release could execute unreviewed code or alter agent behavior at install time.

External Transmission

Medium
Category
Data Exfiltration
Content
### Upload references

```bash
curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/reference.png"
```
Confidence
89% confidence
Finding
The skill instructs uploading user-provided reference images to an external API endpoint, which is a real data-transmission risk because images may contain sensitive personal, biometric, or proprietary content. The danger is elevated by the skill's purpose—editing existing photos often involves faces and other identifying material—and there is no embedded requirement for consent, minimization, or destination verification beyond the example endpoint.

External Transmission

Medium
Category
Data Exfiltration
Content
### Upload references

```bash
curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/reference.png"
```
Confidence
89% confidence
Finding
The skill instructs uploading user-provided reference images to an external API endpoint, which is a real data-transmission risk because images may contain sensitive personal, biometric, or proprietary content. The danger is elevated by the skill's purpose—editing existing photos often involves faces and other identifying material—and there is no embedded requirement for consent, minimization, or destination verification beyond the example endpoint.

External Transmission

Medium
Category
Data Exfiltration
Content
### Upload references

```bash
curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/reference.png"
```
Confidence
89% confidence
Finding
The skill instructs uploading user-provided reference images to an external API endpoint, which is a real data-transmission risk because images may contain sensitive personal, biometric, or proprietary content. The danger is elevated by the skill's purpose—editing existing photos often involves faces and other identifying material—and there is no embedded requirement for consent, minimization, or destination verification beyond the example endpoint.

External Transmission

Medium
Category
Data Exfiltration
Content
### Upload references

```bash
curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/reference.png"
```
Confidence
89% confidence
Finding
The skill instructs uploading user-provided reference images to an external API endpoint, which is a real data-transmission risk because images may contain sensitive personal, biometric, or proprietary content. The danger is elevated by the skill's purpose—editing existing photos often involves faces and other identifying material—and there is no embedded requirement for consent, minimization, or destination verification beyond the example endpoint.

External Transmission

Medium
Category
Data Exfiltration
Content
### Upload references

```bash
curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/reference.png"
```
Confidence
89% confidence
Finding
The skill instructs uploading user-provided reference images to an external API endpoint, which is a real data-transmission risk because images may contain sensitive personal, biometric, or proprietary content. The danger is elevated by the skill's purpose—editing existing photos often involves faces and other identifying material—and there is no embedded requirement for consent, minimization, or destination verification beyond the example endpoint.

External Transmission

Medium
Category
Data Exfiltration
Content
### Upload references

```bash
curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/reference.png"
```
Confidence
89% confidence
Finding
The skill instructs uploading user-provided reference images to an external API endpoint, which is a real data-transmission risk because images may contain sensitive personal, biometric, or proprietary content. The danger is elevated by the skill's purpose—editing existing photos often involves faces and other identifying material—and there is no embedded requirement for consent, minimization, or destination verification beyond the example endpoint.

External Transmission

Medium
Category
Data Exfiltration
Content
### Upload references

```bash
curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/reference.png"
```
Confidence
89% confidence
Finding
The skill instructs uploading user-provided reference images to an external API endpoint, which is a real data-transmission risk because images may contain sensitive personal, biometric, or proprietary content. The danger is elevated by the skill's purpose—editing existing photos often involves faces and other identifying material—and there is no embedded requirement for consent, minimization, or destination verification beyond the example endpoint.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.