Security audit

AURA

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward personality settings helper that changes the agent’s style through a local workspace file.

Install only if you want a workspace-level personality profile. Review AURA.yaml before relying on it, be cautious about adding the optional AGENTS.md startup rule in shared or untrusted repositories, and remember that /aura reset removes AURA.yaml but does not necessarily remove any startup rule you manually added.

A.I.G

Vulnerability Patterns

Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
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

Findings (1)

T02 · Agent Memory Poisoning

Warning

Location: SKILL.md:84
Finding: Persistent Agent Behavior Modification Through Workspace Instructions
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The markdown states that /aura creates or updates AURA.yaml and /aura reset removes it, but it does not include a clear user-facing warning that these commands will modify files in the workspace. Although this is part of the skill's function, the description omits an explicit caution about data/system effects as required for markdown-file warning checks.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.