Security audit

Vince MP CLI Support

Security checks for vulnerabilities and agentic risk

Overview

This skill is a live WeChat Mini Program debugging helper with powerful but disclosed runtime controls and documented safety boundaries.

Install only if you intend to let the agent control a WeChat Mini Program runtime. Use non-production targets when possible, confirm the selected backend environment before env/log commands, provide admin tokens only when needed, and treat tap/input/scan/navigation/storage/media actions as real runtime side effects.

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The README explicitly promotes debugging, environment switching, log retrieval, and runtime interaction against a live WeChat Mini Program, but it does not warn users about the risk of touching production-like systems, exposing user data, or triggering state-changing actions. In a skill designed for live runtime control, omission of safety guidance materially increases the chance of misuse or accidental impact.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/check_battery_clean.mjs:76

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/check_release_gate.mjs:37

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/live-smoke-existing.mjs:32

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/run_all.mjs:49

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/validate-skill.mjs:111