Back to skill

Security audit

muse-illustration

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent illustration skill for turning Chinese poetry or imagery into image prompts, with disclosed image-generation cost and bounded optional case-library updates.

Install if you want a Chinese poetry and imagery illustration workflow. Be aware it may spend image-generation credits, uses style reference images, and can save accepted results back into its own case library when you approve them.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (12)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation description and overall skill framing are written as Chinese-only operating instructions for when the skill should be used, with no indication that other languages are supported or that the user can opt into a preferred locale. This can violate language/locale policy because it imposes a specific language context without documented choice or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The trigger conditions include generic phrases such as '画成画', '出图', '做海报', and '配图', which are common everyday requests and are not tightly constrained beyond broad creative input types. Without negative examples or clearer exclusion boundaries, the skill could activate for many general image-generation requests unintentionally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The comments and lexicon entries are entirely in Chinese, which effectively forces a specific language for users or maintainers interacting with this skill file. Under the policy rule, a language-specific constraint should be optional, user-selectable, or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest content is entirely in Chinese, including the skill name, summary, notes, and descriptive fields, with no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-language audience. This can violate language/locale policy when a skill effectively mandates a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file explicitly mandates '英文撰写提示词' and says Chinese input should be translated into English prompts. This is a language-policy constraint stated as a hard rule, with no user choice or opt-in mechanism, which matches the policy-violation category for forced language/locale behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown template consistently requires Chinese-language content, including headings, field comments, and example values, but does not indicate that Chinese is optional or that the skill is intended only for a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is 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
88% confidence
Finding

The markdown explicitly instructs that {SUBJECT} must be filled with an English subject description. This is a natural-language locale/language constraint, and the file does not state that the user can choose another language or opt in to English output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The natural-language instructions and metadata force a single language/locale presentation, but the file does not document that the skill is Chinese-only or offer any language choice. Under the language/locale policy, a fixed language without opt-in or justification can be a policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

This manifest states that reference-image anchoring is treated as a default action rather than an optional enhancement, but it does not clearly define when that default should or should not apply. Because the file is a manifest and lacks explicit scope limits or negative examples for this behavior, the trigger/activation condition is somewhat ambiguous.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file includes section headers in Chinese only ('单色版', '留红版') while the rest of the prompt is in English, creating a locale-specific instruction pattern without any stated user choice or justification. Under the language/locale policy, forcing or assuming a specific language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

Lines L13 and L18-L20 contain instructional text in Chinese while the rest of the file is in English, effectively imposing a mixed-language usage pattern without any user opt-in or explanation. This matches the policy concern for language/locale constraints expressed in natural language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The prompt explicitly mandates a "Japanese zine / literary-journal aesthetic," which is a natural-language locale/cultural constraint rather than an optional style choice. Under the policy criteria, forcing a specific language/locale-style framing without opt-in can be a violation when no alternative or user choice is offered.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.