Security audit

MLOps Prototyping CN

Security checks for vulnerabilities and agentic risk

Overview

This skill is a notebook checklist tool, but its included checker script has an input-handling flaw that could run unintended local code if used on a maliciously named notebook file.

Review this skill before installing or running it. Its notebook-checking goal is straightforward, but only run the checker on trusted notebook paths or after fixing the script to pass the filename as an argument to Python through a quoted heredoc.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: scripts/check-notebook.sh:6
Finding: Arbitrary Python Code Execution Through Notebook Filename Injection
Content: View full analysis
Remediation: View remediation

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 (2)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The manifest name includes the suffix "-cn", which conventionally indicates a China/Chinese locale variant. In this file, there is no accompanying explanation, opt-in language, or region-specific justification, so it suggests a locale constraint that may violate the language/locale policy.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The manifest-style header names the skill mlops-prototyping-cn, which signals a locale or regional constraint. The document does not explain what cn means, offer the user a language/locale choice, or justify a China-specific scope as a documented regional compliance requirement.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.