Back to skill

Security audit

json-converter

Security checks for vulnerabilities and agentic risk

Overview

This JSON-conversion skill is simple and shows no malicious behavior, but its trigger wording is broad and its API-key requirement is under-explained.

Install only if you understand what backend or script will actually perform the conversion. Before using it with sensitive JSON, confirm whether JSON_API_KEY is required, where it is stored, and whether your input data is sent to an external service.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The 'When to Use' guidance is broad and underspecified, with phrases like 'processing related functionality' and 'Data operations' that could match many unrelated user requests. This increases the chance an agent invokes the skill in contexts the user did not clearly intend, which can lead to unnecessary file processing or external service usage.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation notes an environment variable for an API key but does not clearly warn that the skill depends on credentials and may transmit data to an external service. That omission can cause users or orchestrators to invoke the skill without understanding secret-handling and data-exposure implications, increasing the risk of unintended credential use or sensitive data being sent off-system.

Content

No source excerpt is available for this finding.