Security audit

Kimi Code CLI

Security checks for vulnerabilities and agentic risk

Overview

The skill appears purpose-built for running Kimi CLI on coding tasks, but it needs review because it can generate unsafe shell commands and asks for broad local execution authority.

Install only in a controlled environment, prefer a pinned and reviewed Kimi CLI version inside a virtualenv, run it in a dedicated project directory, do not pass untrusted task text or paths through the bundled runner, and verify any background Kimi session is killed after use.

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: scripts/kimi_runner.py:24
Finding: Command Injection Through Unescaped Task and Working-Directory Inputs
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:217
Finding: Unpinned Third-Party CLI Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill explicitly instructs the agent to create/modify files and invoke shell-based tooling, but it does not include a clear safety notice about possible effects on the local filesystem, existing project contents, or installed environment. In practice, this can cause unintended overwrites, dependency changes, or execution in the wrong directory, especially because the skill is designed for autonomous multi-step coding tasks.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill documents background interactive sessions and process control, including submit/write/kill operations, but does not prominently warn that these subprocesses may continue running, consume resources, or keep modifying state unless actively monitored and terminated. That creates operational risk: orphaned sessions, unintended long-running tasks, and harder-to-notice ongoing filesystem or environment changes.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.