Ae5
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Instruction-capable artifact exceeds whole-file semantic analysis limits
- Content
Security audit
雀漫
Security checks for vulnerabilities and agentic risk
Overview
This is a mostly text-only storyboard skill, but its bundled examples turn illegal excavation and explosive-use scenes into actionable production scripts without safety limits.
Review before installing if this will be used on arbitrary novels or user-submitted text. The main risk is not local system compromise; it is that the skill may convert dangerous criminal or explosive scenes into clearer scripts unless the user or host adds safeguards to keep such scenes non-actionable and lawful.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)
Missing User Warnings
High
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
This content provides concrete operational details for illegal tomb-robbing and explosive breaching, including use of TNT, hole construction, concealment, and the advantages of the technique, without any safety, legal, or refusal framing. Because the skill is meant to transform source text into polished video storyboards, it can repackage harmful procedural content into clearer, more usable instructions, increasing misuse risk rather than merely depicting fiction.
- Content
Missing User Warnings
High
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The narrative includes actionable criminal tradecraft such as handling a盗洞, rotating operators, lookouts, air exchange/'泄阴气', and methods for restoring the ground to hide evidence. Even if presented as fiction, these specifics can instruct or normalize real-world illegal excavation and hazardous confined-space entry, and the skill context may preserve or sharpen these details in output.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
The file is written entirely in Chinese and presents all prompts, outputs, and operating instructions in Chinese, but it does not state that language selection is optional or limited for a justified regional reason. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger list contains broad terms such as 小说改编, 故事结构, and 动态漫画 that can match ordinary creative-writing or story-structure requests not specifically intended for this skill. This can cause overbroad activation, pulling the user into a rigid multi-step workflow unexpectedly and increasing prompt-surface exposure to unrelated user content.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
This markdown file contains natural-language requirements such as '旁白必须标注音色' and a gender dimension limited to '男声/女声', followed by recommended fixed gendered combinations for scene types. That can amount to a language/locale-style policy issue because it imposes a specific presentation choice without user opt-in or an explicit justification for why gender must be constrained this way.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
This markdown file contains natural-language constraints based on Chinese character counts per second and recommended output content in Chinese, which effectively imposes a specific language/locale assumption. The policy allows locale constraints only when the skill offers user choice or clearly documents a justified region-specific need, neither of which is present here.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The title and all instructional content are written exclusively in Chinese, and the document presents the guidance as a normative specification without indicating that language choice is optional. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation unless clearly justified as region-specific.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill content is entirely in Chinese and prescribes Chinese-only output structure without offering a user language choice. This can cause users to receive instructions or generated content in a language they do not understand, increasing the risk of misunderstanding, unsafe downstream use, and exclusion of users who need another language for review or validation.
- Content