Back to skill

Security audit

Rustic Almanac Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only lifestyle and weather advice skill with no code, install hooks, persistence, or credential handling.

Install this if you want a stylized daily almanac-style guide. Treat its health, work, and investment suggestions as general lifestyle advice, and expect a folksy tone unless you ask the agent to answer plainly.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger description is broad enough to activate on common, generic requests such as daily advice, planning the day, or 'what's the vibe today.' Overly broad invocation can cause the skill to intercept unrelated conversations and steer responses into its prescribed persona and advice format, reducing user control and increasing the chance of inappropriate or off-target guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The skill hard-codes a specific persona, rustic tone, and bilingual stylistic framing without any user opt-in. While not directly unsafe, this can override user preferences or system expectations for tone and language, leading to misaligned responses and a mild form of prompt-level control over the assistant's behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.