Back to skill

Security audit

writER

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only writing-style skill with no code execution, credentials, persistence hooks, or hidden data access.

Install this if you specifically want Chinese poetic prose in the ER style. Be aware that broad trigger phrases such as general requests to write prose may cause the agent to apply this style unexpectedly; ask explicitly for another style or disable the skill for neutral writing tasks.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This skill documentation forces a specific language context for installation and usage guidance, which can violate language/locale policy when no user opt-in or alternative is provided. The file does not indicate that the skill is region-specific or that Chinese is an optional presentation choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill description hardcodes a particular personal writing style and Chinese poetic-prose output mode without indicating user choice, fallback behavior, or opt-in controls. In practice, this can override user intent, produce unwanted stylistic transformation, or force a locale/style that is inappropriate for the requested task.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger keywords are broad, generic phrases such as '帮我写散文', '写成文章', and '改成我的风格', which can match many ordinary writing requests unrelated to this specific skill. This can cause unintended invocation and style hijacking, leading the agent to apply the skill in contexts where the user did not explicitly consent to this transformation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The title and all transformation rules are written as mandatory Chinese-writing guidance for converting oral language into poetic prose. The document does not indicate that language selection is optional or user-driven, which can violate a language/locale policy requiring user choice unless the constraint is clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The markdown content is entirely in Chinese and does not indicate that language selection is optional or that the skill is intentionally region-specific. 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.