Security audit

八要素法文献阅读

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent academic paper-reading helper with disclosed network lookup and note-taking behavior, but users should keep control over local fetches and note-file writes.

Install only if you want a Chinese-default academic reading workflow. Before allowing it to run local curl commands or append to a notes file, confirm the exact link and file path, and do not use it to access paywalled or otherwise unauthorized content.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly instructs the agent to use local PowerShell curl.exe to fetch restricted links, which expands behavior from passive analysis into active network/tool use against access-controlled content. Even if framed as a convenience for obtaining paper text, this can lead to unauthorized retrieval attempts, inconsistent enforcement of access restrictions, and use of local execution capabilities in ways the user may not expect.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The invocation text is very broad: telling users to simply send a paper and say a generic phrase like '精读这篇' can overlap with ordinary conversation and cause unintended skill activation. In agent systems, ambiguous triggers can route unrelated content into the skill, leading to inappropriate handling of user data, confusing behavior, or prompt-surface expansion when external paths/links are accepted.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: All user-facing instructions and invocation examples in the file are Chinese-only, and there is no indication that users may interact in another language or opt into this locale. Under the policy, forcing a specific language without user choice can be a natural-language policy violation unless the restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill directs the agent to append notes to a local literature-note file by default, but does not require explicit per-action confirmation before modifying user files. This creates a risk of unintended local data modification, corruption of an existing notes file, or writing sensitive paper summaries into an unexpected workspace location.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file presents all instructions and output templates exclusively in Chinese, and does not indicate that the user can choose another language. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.