Security audit

AI Engineer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent AI engineering reference guide with some simplified examples that need careful adaptation before production use.

Install is reasonable for AI engineering reference use. Treat the code snippets as starting points only: add explicit authorization and schema validation for tool calls, keep retrieved documents as untrusted evidence rather than privileged instructions, and define consent, retention, deletion, and redaction rules before implementing long-term memory.

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 (2)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:67
Finding: Retrieved Content Is Injected into a Privileged System Message
Content: View full analysis
Remediation: View remediation
\n{context}\n", }, ] ``` This structure reduces message-role confusion but must still be combined with external access control and tool-policy enforcement. ]]>

T09 · Insecure Skill Coding Practices

Error

Location: references/agent-patterns.md:19
Finding: Model-Generated Tool Calls Are Dispatched Without Authorization or Argument Validation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The long-term memory example shows saving and retrieving conversation-derived data from an external store without any warning, consent flow, retention limits, or guidance on filtering sensitive content. In an AI engineering skill, this pattern is likely to be copied into production systems, which can lead to unintentional storage of personal, confidential, or regulated data and later retrieval into prompts.
Content: No source excerpt is available for this finding.