Security audit

Axodus Backend Architecture

Security checks for vulnerabilities and agentic risk

Overview

This is a simple backend architecture guidance skill; its trigger metadata is malformed, but the artifacts do not show unsafe behavior.

This skill appears safe to install as backend design guidance, but the publisher should replace the malformed trigger metadata with explicit backend-architecture activation phrases to avoid unexpected invocation.

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: 98% confidence
Finding: The trigger configuration is effectively unconstrained: triggers: System.Object[] does not define concrete activation phrases, schemas, or limits for when this skill should run. In an agent environment, ambiguous activation can cause the skill to be invoked unexpectedly or too broadly, increasing the chance of misuse, unintended backend-design actions, or policy bypass through overly permissive routing.
Content: No source excerpt is available for this finding.