Back to skill

Security audit

ai-note-of-video

Security checks for vulnerabilities and agentic risk

Overview

This skill documents a purpose-aligned service that sends public video URLs to HeyBossAI/SkillBoss for note generation, with no bundled code, persistence, or hidden local access found.

Install only if you are comfortable sharing submitted video URLs with HeyBossAI/SkillBoss. Use public, non-sensitive URLs only, and do not submit private, internal, signed, or token-bearing links. Note that the referenced helper scripts are not included in this artifact, so functionality may be incomplete without additional files.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation instructs users to submit a video URL to a third-party endpoint but does not clearly warn that the provided URL will be transmitted to an external service. This can mislead users into sharing internal, sensitive, or access-controlled URLs without informed consent, creating privacy and data-handling risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

This skill sends user-supplied video URLs to an external API endpoint operated by a third party. Even if this is the intended functionality, it creates a real data-exposure boundary because URLs may contain sensitive identifiers, signed tokens, internal hostnames, or links to non-public resources.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
### Generate Notes

**Endpoint**: `POST https://api.heybossai.com/v1/pilot`

**Parameters**:
- `video_url` (required): Public video URL

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The query flow also posts the user-provided video URL to the same third-party API, so the same external disclosure and privacy concerns apply here. Repeating the transmission path increases the chance that a user misunderstands where their data is going, especially since the skill presents the operation as a simple notes-generation workflow.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

md
### Query Notes

**Endpoint**: `POST https://api.heybossai.com/v1/pilot`

**Parameters**:
- `video_url` (required): Public video URL (SkillBoss API Hub returns results synchronously)