Security audit

Daily Dungeon Challenger

Security checks for vulnerabilities and agentic risk

Overview

This is a low-impact text planning skill that reads its own markdown and does not access accounts, credentials, networks, calendars, or persistent system state.

Installers should treat this as a lightweight planning prompt, not a calendar or project-management automation. It appears safe from a security perspective, but users expecting a fully generated, personalized daily plan may find the current handler mostly repeats the skill template unless the host agent applies the markdown workflow itself.

A.I.G

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

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (5)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: This is a clear description-behavior mismatch. The declared purpose promises a concrete planning workflow that transforms a user's day into a game-like structure with specific planning elements. The actual handler is a generic markdown/template introspection renderer: it loads SKILL.md, extracts sections like purpose/workflow/output format, echoes user context, and returns a formatted guidance card. While it may display text from a prompt template that mentions planning, the code itself does not carry out the described daily-planning function. There are no external actions or suspicious permissions, but the primary purpose is materially different from what was declared.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The declared purpose promises a user-facing planning skill that transforms a day into a dungeon/side-quest structure. The actual code chunk only contains tests asserting that metadata and prompt-template sections load and that handle() returns a descriptive card with workflow/output-format text and the original input. Based on this code, the observable behavior is documentation/template verification, not generation of a structured daily plan with win conditions, time budgets, fallback modes, or reward prompts. This is a material description-behavior mismatch.
Content: No source excerpt is available for this finding.

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.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The 'Use this skill when' section describes broad situations such as having too many tasks, wanting a morning plan, or procrastinating because the day feels shapeless. These are common everyday conditions, and the file does not provide tighter trigger constraints or negative examples clarifying when this skill should not be invoked.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The file includes 'Chinese name: 每日副本挑战' as a locale-specific label, but it does not explain whether this is optional metadata or part of a user-facing language behavior. Because no user language choice or locale justification is provided, this may create ambiguity around language policy compliance.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.