Security audit

Phy Architect Mentor

Security checks for vulnerabilities and agentic risk

Overview

This is a low-impact instructional architecture coaching skill with no executable code, privileged access, or persistence; the only notable caveat is broad activation wording.

This skill appears safe to install for architecture coaching. Be aware that ordinary phrases like asking how to do architecture may trigger it; use the explicit /architect-mentor command when you want predictable activation.

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

Confidence: 95% confidence
Finding: The manifest description includes broad natural-language trigger phrases such as '教我架构' and '怎么做架构', which can overlap with ordinary user conversation and cause the skill to activate unintentionally. While the skill content itself is instructional and not overtly dangerous, broad activation increases the chance of unexpected invocation, context switching, or prompt-surface expansion in unrelated conversations.

Static analysis

No suspicious patterns detected.