Back to skill

Security audit

什么值得做 Stringer

Security checks for vulnerabilities and agentic risk

Overview

The skill provides market research through a named external service, with proportionate query sharing and optional preference memory.

MCP requests send a short summary of your question to stringers.io; keep confidential project details out. The public-JSON route allows personalization locally. Requested daily briefings can save your agreed profile and preferences in memory. The external MCP service's implementation and retention practices were not reviewed.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

User intent is sent to an external service without a privacy disclosure.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The skill requires sending a paraphrase of the user's current objective through the external stringer tools' ask parameter without requiring disclosure or authorization for sharing that context. Excluding names and contact details reduces exposure, but the summary can still reveal confidential product plans, target markets, or business strategy; this is task-related data sharing with insufficient privacy safeguards, not evidence of malicious exfiltration.

Content

No source excerpt is available for this finding.

Activation includes generic questions without requiring business-opportunity intent.

Low
Category
Trigger Abuse
Confidence
91% confidence
Finding

The description directs activation for questions such as “现在做什么” (“what should I do now”) and questions about whether a user's project is heading in the right direction. These can refer to ordinary task planning or technical decisions, but the activation instructions do not explicitly require product-market or business-opportunity intent.

Content

No source excerpt is available for this finding.