Security audit

Osmotic Pressure

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only architecture analysis skill with no code execution, network use, persistence, or credential handling; its invocation wording is broad but not dangerous.

Installers should expect this skill to influence architecture review conversations and possibly be invoked in broad design discussions. It does not add executable code or special access, but users who want tighter activation may prefer more explicit trigger wording.

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: 92% confidence
Finding: The 'When to Invoke' section lists generic situations such as 'During architecture design' and 'When one module seems to attract all the bugs' without defining specific trigger phrases, scope boundaries, or exclusion conditions. In a markdown skill description, this is broad enough to overlap with common software discussions and may cause unintended invocation.

Static analysis

No suspicious patterns detected.