Back to skill

Security audit

agent-directory-listing

Security checks for vulnerabilities and agentic risk

Overview

The scanners classified this skill as benign because they found no reported malicious behavior, while noting that it may send user-provided URLs to a third-party service without disclosure.

Consider whether the URLs you provide are public. Avoid sending URLs with credentials or private details unless you are comfortable with them being sent to whywontai.com; the scan was partial, so its evidence is incomplete.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow sends user-provided URLs to a third-party service without a user-facing disclosure.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The workflow instructs the agent to send a user-provided product site or MCP URL to the third-party whywontai.com service without requiring a user-facing disclosure. This can expose confidential product hostnames or sensitive URL components if supplied, although the intended use with public product sites substantially limits the typical impact. The endpoint is openly documented in the skill, and there is no evidence of malicious intent or broader data collection.

Content

No source excerpt is available for this finding.