Back to skill

Security audit

职业教育课材一体化开发

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a small vocational-education helper with only local language-support code and no evidence of hidden access, persistence, or data movement.

Review the language behavior if you need English by default, and note that the package would be clearer with declared tool permissions; otherwise the inspected files show no hidden or high-impact security behavior.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Dynamic import via __import__()

Medium
Category
Dangerous Code Execution
Confidence
75% confidence
Finding

Dynamic import() can load arbitrary modules at runtime, bypassing static analysis and potentially importing malicious code.

Content

Scanner excerpt · i18n_helper.py (reported line 26)May include surrounding context.

python
return json.load(f)
            return {}
        except Exception as e:
            print(f"Error loading i18n.json: {e}", file=__import__('sys').stderr)
            return {}

    def _detect_language(self):

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code enforces a default of 'zh' whenever HERMES_LANG or LANG do not clearly indicate 'zh' or 'en'. That creates a language/locale policy issue because the skill forces a specific language choice instead of offering a neutral fallback or requiring user opt-in.

Content

No source excerpt is available for this finding.