Back to skill

Security audit

Nbnhhsh Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple pinyin-initialism lookup helper, but users should know it sends lookup text to a third-party API.

Install only if you are comfortable sending abbreviation queries to lab.magiconch.com. Avoid using it with secrets, personal data, or confidential text, and prefer explicit short abbreviation lookups rather than vague prompts.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to activate on common conversational inputs like 'don't understand' or 'what's this', which can cause the skill to run outside its intended niche. In context this is not directly dangerous code execution, but it can lead to unnecessary invocation of the external service and accidental transmission of user-provided text.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs sending user input to a third-party API but does not clearly warn that the query leaves the local system. This creates a privacy and consent risk, especially if users paste sensitive text that merely resembles an abbreviation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The documented behavior performs a POST request to an external domain with user-supplied text, which is an external data transmission path. In this skill's context the transmitted content is usually short abbreviations, so the danger is moderated, but any mis-trigger or careless use could still leak sensitive user content to a third party.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

Run curl:

bash
curl -s -X POST "https://lab.magiconch.com/api/nbnhhsh/guess" \
  -H "Content-Type: application/json" \
  -d '{"text":"abbreviation to query"}'

Static analysis

No suspicious patterns detected.