Security audit

Sv Caption Design

Security checks for vulnerabilities and agentic risk

Overview

This is a document-only caption design guide with minor scoping and language clarity issues but no code, credentials, network use, persistence, or hidden authority.

This skill is reasonable to install if you want guidance on short-video caption styling. Be aware it may activate for broad caption-related requests, and users who need non-English output may want to specify their preferred language explicitly.

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

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 keywords are broad, generic phrases such as 'video captions' and 'subtitle design' without boundaries on when the skill should or should not activate. This can cause over-triggering in unrelated captioning or accessibility contexts, leading the agent to invoke the skill inappropriately and potentially override more relevant guidance, though the content here is non-sensitive and does not itself appear malicious.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The trigger section lists generic phrases such as "video captions," "subtitle design," and "text overlay" without constraints, negative examples, or a clear activation boundary. In a markdown skill description, this can cause unintended invocation because these phrases are common in normal creative discussions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: Scenario 4 presents the interaction and expected output entirely in Chinese, including prescriptive recommendations, but the document does not state that the skill is region-specific or that users can choose their preferred language. This may imply a locale-specific response mode without explicit opt-in, which conflicts with language-choice expectations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest sets "language": "en", which indicates a fixed language constraint. Under the policy, locale or language restrictions should either offer user opt-in/choice or be clearly justified as region-specific; this file provides neither.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The checklist explicitly requires "English-first documentation," which is a natural-language locale constraint. Under the policy, forcing a specific language without offering user choice or documenting a justified regional limitation is a violation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.