Back to skill

Security audit

Allergy Season Room Routine

Security checks for vulnerabilities and agentic risk

Overview

This is a document-only allergy-season room routine skill with clear medical safety boundaries and no code, network, credential, persistence, or hidden execution behavior.

Before installing, users should understand that this skill provides practical home-routine suggestions, not medical advice. It is appropriate for low-risk room habits, but users should seek urgent local care for breathing trouble, swelling, chest tightness, severe reactions, or symptoms that feel dangerous.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Line L08 states 'Public-facing documentation is English only,' which is a natural-language locale restriction. The file does not provide user opt-in, multilingual support, or a documented region-specific justification for this constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L15 says 'No CJK characters are present,' which imposes a character-set and language-related restriction rather than a functional or safety requirement. No user opt-in or justified business/regional necessity is given, so this appears to violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L23 requires 'English/ASCII only,' which is a natural-language and character-set limitation. The file does not explain why non-English or non-ASCII content would be disallowed, nor does it offer user choice or a region-specific rationale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest sets the skill language to "en", which can constitute a language/locale policy issue when the skill appears generally applicable and does not indicate user opt-in or a documented regional justification. In this file, there is no accompanying note that the language restriction is optional or required for a specific compliance or regional purpose.

Content

No source excerpt is available for this finding.