Security audit

Aibrary 100

Security checks for vulnerabilities and agentic risk

Overview

This is a simple book-recommendation skill with no code execution, persistence, credential use, or hidden data access.

This appears safe to install as a reading-list helper. Be aware that generic prompts about must-read or essential books may invoke Aibrary's curated framework even when you wanted a broader, non-branded recommendation set.

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: 94% confidence
Finding: The trigger phrases are broad enough to activate on generic requests like 'must-read books' or 'best books for the AI age,' which can cause the skill to intercept ordinary recommendation queries beyond its narrow intended use. This is not code-execution dangerous, but it can misroute user intent, reduce response quality, and create unnecessary overreach in agent behavior.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.