Security audit

Nsfc

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Chinese NSFC grant-writing helper with no executable code, persistence, or hidden data access.

Install only if you want Chinese-language help drafting or reviewing NSFC applications. Use explicit nsfc-prefixed requests where possible, verify current NSFC rules yourself, and do not rely on the skill to invent or validate citations without source checks.

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
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 (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The report documents legacy trigger examples such as write, review, outline, template, and checklist as standalone one-word commands. In chat-based or natural-language agent environments, such broad triggers can collide with ordinary user speech and unintentionally activate the skill or its compatibility layer, causing prompt-routing confusion or unauthorized handling of sensitive proposal content.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file uses only Chinese for headings, instructions, and operational notes, but does not mention that the skill is Chinese-only or offer users a language/locale choice. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description, argument hints, title, and command examples are presented entirely in Chinese, which imposes a specific language on users. The file does not offer an alternative language, opt-in choice, or a documented justification that the skill is intentionally limited to a Chinese-only audience or region.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The package description forces a single language presentation in Chinese and does not state that the skill is intended only for Chinese-speaking users or offer any language choice. Under the policy criteria, a language-specific constraint should be explicit and justified or presented as an opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.