Back to skill

Security audit

interview-question-kit

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: the scanners found no AIG issues, while Skillspector noted a mismatch between the skill’s stated interview-kit purpose and the reported script behavior, plus undeclared file-writing capability.

Before installing, consider whether a skill that the scanner reports as checking existing interview content and writing a lint report fits your needs. Skillspector’s analysis was partial because several referenced paths were unresolved, so the benign verdict is not a guarantee that all behavior was assessed.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied script's primary function is linting, not building the interview kit promised by the description. It does not create role-specific questions, follow-up probes, competencies, or scoring criteria; it merely checks whether corresponding section labels occur in supplied text. Its banned-phrase checks partially support the declared flagging function but are narrow and context-insensitive, including flagging phrases quoted in a do-not-ask list. File reads and report writes are ordinary supporting implementation details; no unrelated resource access or hidden capabilities are evident.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

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.