Security audit

【官方】知识星球·用户查询

Security checks for vulnerabilities and agentic risk

Overview

The skill’s purpose is coherent, but its NPS workflow shows unsafe shell-command handling and a mutable global install recommendation that should be reviewed before use.

Review this before installing. Only submit NPS feedback after explicit confirmation, treat profile and footprint JSON as private account data, and avoid running NPS suggestions through shell-constructed commands. Prefer a pinned, reviewed `zsxq-cli` version and direct argument-array execution for user-supplied feedback.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Error

Location: references/zsxq-user-nps.md:27
Finding: Shell Command Injection Through User-Controlled NPS Feedback
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: references/zsxq-user-nps.md:66
Finding: Unpinned Global Installation of a Mutable npm Dependency
Content: View full analysis
Remediation: View remediation

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 (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The markdown states that the command retrieves the current account's complete profile, including user ID, location, authentication status, and subscription information. This is sensitive personal/account data, but the document provides no warning about privacy implications, handling of the JSON output, or caution when sharing or storing the result.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The activation guidance encourages proactive invocation when a user expresses dissatisfaction, perceived product gaps, or repeated frustration. Because this command performs a write action that submits feedback to an external service, broad trigger language can lead the agent to initiate or steer toward submission without a sufficiently explicit user request, increasing the risk of unintended actions or manipulation of user sentiment into outbound feedback.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.