Back to skill

Security audit

Sv Script Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a document-only short-video scripting guide with no executable code, network use, credential handling, or persistence.

Installers should understand this skill is a writing template for short videos. The main caveat is that its trigger keywords are somewhat broad, so it may be selected for adjacent script or video-writing requests where another writing skill might fit better.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is broad and generic enough to match many ordinary writing requests, which can cause the skill to activate outside its intended scope. While this is not a code-execution issue, overbroad activation can lead to unintended routing, user confusion, and inappropriate application of the skill in contexts where a more suitable tool should handle the request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords are overly generic for common writing-assistance requests such as 'write video' and 'script structure', which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of unintended prompt interception, routing conflicts, or inappropriate application of the skill to general user requests, though the skill itself is otherwise low risk and contains no obviously malicious behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrase "write video" is ambiguous and not narrowly scoped to short-video script generation. It could overlap with common user phrasing about video creation or editing, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest sets the skill language to "en" with no indication that users can choose another language or that the restriction is required for a justified regional purpose. This creates a natural-language policy concern because it hard-codes a locale preference without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The checklist explicitly states "English-first documentation," which is a natural-language locale preference. Under the policy rules, forcing a specific language without user choice or a documented region-specific justification is a policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.