Security audit

ml-engineer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown ML engineering guidance skill with no executable code, hidden persistence, credential handling, or unrelated data flows.

Install this if you want an agent persona for ML engineering work. Review any concrete changes it proposes to ML infrastructure, deployment, monitoring, or retraining before applying them, but the skill package itself does not contain executable or hidden privileged behavior.

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This markdown file describes behavior 'When invoked' but never defines what phrases, contexts, or constraints actually cause invocation. The lack of explicit trigger scope or exclusion conditions makes activation semantics overly broad and could lead to unintended use.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.