ClawHub
Back to skill

Security audit

p-video-edit

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Pruna cloud video-editing guide, with expected uploads and API use but some privacy and supply-chain cautions users should understand.

Before installing or using this skill, understand that source videos and optional reference images are uploaded to Pruna's remote API and may contain sensitive personal or proprietary content. Use it only for media you are authorized to upload, review Pruna's data handling terms, and prefer pinned or trusted versions of the related skills where possible.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (22)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
`prompt` is **surgical** and **request-locked**. One principal change per run. Describe the desired final state, then name what must stay unchanged. Change only what the user asked; keep camera, motion, audio, and unmentioned elements identical.

| Do                                                                                                   | Don't                                                                            |
| ---------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- |
| Formula: `Change only [X]. Preserve [geometry / motion / camera / lighting / unmentioned subjects].` | Vague `make it better` / mood-only rewrites that invent a new scene              |
| Name every **must-keep** from the user (subject, camera path, lighting, props)                       | Drop keep-clauses and hope the model preserves them                              |

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs agents to upload user source videos and optional reference images to a remote API but provides no explicit privacy, retention, consent, or data-handling warning. Because these assets may contain sensitive personal, biometric, or proprietary content, silent transmission can violate user expectations and organizational data-governance requirements.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This command uploads a local video file to an external service using an API key. External transmission is expected for a cloud video-editing skill, but it is still security-relevant because user media may contain sensitive data and the skill text does not pair the upload step with explicit consent, classification, or handling safeguards.

Content

Scanner excerpt · SKILL.md (reported line 74)May include surrounding context.

Upload source video

bash
curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/source-video.mp4"

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This command uploads a local video file to an external service using an API key. External transmission is expected for a cloud video-editing skill, but it is still security-relevant because user media may contain sensitive data and the skill text does not pair the upload step with explicit consent, classification, or handling safeguards.

Content

Scanner excerpt · SKILL.md (reported line 74)May include surrounding context.

Upload source video

bash
curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/source-video.mp4"

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

This section instructs uploading optional reference images to a third-party API without an explicit warning that the images leave the local environment. Reference images can include faces, products, documents, or other sensitive material, so unqualified transmission increases privacy and compliance risk.

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

Optional reference images

bash
curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/reference-image.png"

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 94)May include surrounding context.

Create (async — recommended)

bash
curl -X POST 'https://api.pruna.ai/v1/predictions' \
  -H 'Content-Type: application/json' \
  -H "apikey: ${PRUNA_API_KEY}" \
  -H 'Model: p-video-edit' \

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 100)May include surrounding context.

Create (async — recommended)

bash
curl -X POST 'https://api.pruna.ai/v1/predictions' \
  -H 'Content-Type: application/json' \
  -H "apikey: ${PRUNA_API_KEY}" \
  -H 'Model: p-video-edit' \

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 113)May include surrounding context.

Create (async — recommended)

bash
curl -X POST 'https://api.pruna.ai/v1/predictions' \
  -H 'Content-Type: application/json' \
  -H "apikey: ${PRUNA_API_KEY}" \
  -H 'Model: p-video-edit' \

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 120)May include surrounding context.

Create (async — recommended)

bash
curl -X POST 'https://api.pruna.ai/v1/predictions' \
  -H 'Content-Type: application/json' \
  -H "apikey: ${PRUNA_API_KEY}" \
  -H 'Model: p-video-edit' \

Static analysis

No suspicious patterns detected.