Security audit

Aura Image Gen

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-guidance skill for social media image cards, with no executable code, persistence, credential use, or hidden system changes.

Before installing, understand that the skill may route broad image requests into a social-media-card workflow and may translate or adapt prompt text for platform defaults. Avoid sending private or sensitive text to any external image-generation tool unless you are comfortable with that provider handling it.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (9)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list is overly broad because generic phrases like 'generate image' and 'draw' can activate this skill in many unrelated contexts, causing the agent to route requests to an image-generation workflow when the user may have intended something else. This can degrade safety and reliability by creating inappropriate tool selection, prompt injection exposure from unrelated inputs, or accidental handling of content outside the skill's intended domain.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: Mandating English prompts without user opt-in can override user intent and create silent data transformation, especially for multilingual or sensitive text where wording precision matters. While not directly a code-execution issue, it can lead to privacy, correctness, and trust problems if user-provided Chinese or bilingual content is reformulated unexpectedly before being sent to an external image model.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The workflow states language-based platform restrictions such as '中文科普 → xiaohongshu' and '英文教程 → pinterest', and later hard-codes Chinese text for xiaohongshu prompts and English text for pinterest/instagram prompts. This imposes a language/locale policy in the skill description rather than offering the user a choice or documenting opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This markdown file contains substantial Chinese-only natural-language guidance such as platform labels, safe-zone notes, and layout descriptions, but it does not indicate that the skill is intentionally region-specific or provide an opt-in language choice. Under the policy rule, forcing a specific language without user choice can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The document begins with Chinese-only instructional content ("多平台图片生成规格详解。") and the remainder of the guidance is primarily written in Chinese. Under the policy, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The heading includes a Chinese style label "高冲击力风" alongside the English title, which imposes a specific language representation in the preset without indicating that language choice is optional. Under the stated policy, locale or language constraints should be opt-in or clearly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The document is written primarily in Chinese and labels the style with a Chinese title, but does not indicate that language is optional or limited to a region-specific use case. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The title includes Chinese text '(玄学神秘风)', which imposes a specific language presentation in the skill content without indicating user choice or opt-in. This matches the language/locale policy concern for natural-language policy violations because no alternative language option or justification is provided.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The natural-language instruction mandates a specific punctuation convention for Chinese content: use ""，。！punctuation. This is a locale-specific formatting requirement presented as a hard rule, and the file does not indicate that users can opt in or choose a different locale/style preference.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.