Back to skill

Security audit

Find Community

Security checks for vulnerabilities and agentic risk

Overview

This is a guidance-only startup community discovery skill with no code execution, data access, persistence, or hidden behavior.

Installers should expect this skill to provide Chinese-language startup-community coaching. Consider narrowing its trigger phrases or adding language preference guidance, but no sensitive access or execution behavior was found.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger keyword at line 10 ("find community") is broad and can match common entrepreneurial or self-help requests that are not specifically asking for this skill. Over-broad activation can cause unintended skill invocation, steering user interactions unexpectedly and creating prompt-routing ambiguity, though the skill content itself is not overtly harmful.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger keyword at line 13 ("我该做什么业务") is highly ambiguous and overlaps with everyday entrepreneurial discussion. This can cause the skill to activate in many unrelated contexts, increasing the chance of misrouting, unwanted instruction injection into normal conversations, or suppression of better-matched skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

All user-facing description and operating instructions are written exclusively in Chinese, with no indication that the user can choose another language. This can violate a language or locale policy when the skill implicitly constrains interaction language without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.