Security audit

paper-introduction-writer

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent academic-writing skill with disclosed local Markdown output and no evidence of hidden code, network access, credential use, or persistence beyond generated draft files.

Before installing, note that a complete-generation task may create English and Chinese Markdown drafts in your current working directory. For sensitive unpublished research, ask for inline-only output, a specific path, or a single language, and review citation placeholders or any practice-only fake references before reuse.

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
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 (11)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill says it should activate when any of several broad conditions are met, including generic requests like writing an introduction, generating one from a topic, revising an existing draft, or adjusting to a journal style. These triggers are not tightly scoped with exclusion conditions, so they could cause unintended invocation for many ordinary writing-assistance requests that may not specifically require this framework.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill defaults to saving outputs to files in the user's current working directory without explicit opt-in at the decision point. Automatic file creation can cause unintended workspace modification, overwrite risk, or silent artifact generation, especially if the user expected inline-only output.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The workflow states that complete generation defaults to an English output and a Chinese annotated output, regardless of whether the user requested Chinese. This is a natural-language policy issue because it forces a specific locale/language behavior without offering a choice or requiring user opt-in.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This section operationalizes the default file-writing behavior by instructing creation of two Markdown files in the working directory, again without an explicit warning or consent step immediately before the save action. In agentic environments, silent writes are dangerous because they modify user state and may create, replace, or clutter files the user did not intend to generate.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The document is written entirely in Chinese and repeatedly requires Chinese annotations and section labels, such as the checklist items requiring a Chinese version with per-sentence functional notes. This constitutes a natural-language locale constraint, and the file does not indicate user opt-in or a justified region-specific reason for forcing Chinese.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This markdown file contains instructional content exclusively in Chinese, with no statement that the skill is region-specific or that users may choose another language. That can conflict with language/locale policy expectations when users have not opted into Chinese-only output.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown file contains user-facing instructional content exclusively in Chinese, including the title and all explanatory sections. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative language option or justification is provided.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The specification says the skill will, by default, generate and save two files in the user's current working directory, including a Chinese annotated version, unless the user asks otherwise. This creates an overproduction and persistence risk: user-provided research content may be written to disk in multiple artifacts without explicit opt-in, increasing unintended disclosure, workspace clutter, and the chance that sensitive draft content is stored or synced somewhere the user did not intend.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This markdown file presents its instructional content in Chinese from the outset and does not indicate that users may request another language. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is explicitly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 77% confidence
Finding: Line L118 explicitly singles out Chinese output ("若输出中文版") as a mode the skill may produce, but the file does not state that language selection must follow the user's preference or explicit opt-in. This can create a locale/language policy issue because the skill behavior may default to or steer toward a specific language without documented user choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The instruction explicitly requires generating a Chinese annotated version as part of the workflow, which imposes a language choice in natural-language guidance. There is no indication here that the user can opt for another language or that the Chinese requirement is limited to a justified locale-specific use case.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.