ClawHub
Back to skill

Security audit

mixpeek-video-search

Security checks for vulnerabilities and agentic risk

Overview

The skill uses Mixpeek to index and search selected media, with disclosed cloud processing and capped usage costs.

Mixpeek receives search queries and processes the media you select. Share only authorized content, limit storage access to the intended bucket or prefix, and review retention, sync settings, and processing costs. The linked [storage guide](https://mixpeek.com/docs/integrations/object-storage/overview) explains scoped connections.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 37)May include surrounding context.

A public retriever over a small sample of stock footage answers without authentication:

bash
curl -s -X POST https://api.mixpeek.com/v1/public/retrievers/footage-intelligence-sample/execute \
  -H "Content-Type: application/json" \
  -d '{"inputs": {"query": "waterfall from above"}}'

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 37)May include surrounding context.

A public retriever over a small sample of stock footage answers without authentication:

bash
curl -s -X POST https://api.mixpeek.com/v1/public/retrievers/footage-intelligence-sample/execute \
  -H "Content-Type: application/json" \
  -d '{"inputs": {"query": "waterfall from above"}}'

The storage-sync workflow lacks a privacy warning about third-party access to user media.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The skill instructs the agent to create a storage connection and bucket sync for files in S3 or GCS. Although Mixpeek is identified as the indexing service, the workflow does not warn that connecting private storage makes selected user media available to a third party for processing.

Content

No source excerpt is available for this finding.