Back to skill

Security audit

board-game-night-dealer

Security checks for vulnerabilities and agentic risk

Overview

This skill is an offline board-game recommendation helper with disclosed local rotation tracking and no evidence of hidden or harmful behavior.

Install only if you are comfortable with the skill creating or updating a local game_night.json file to remember rotation and recent picks. It does not show evidence of network access, credential handling, or background persistence.

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 (8)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 35)May include surrounding context.

md
python3 scripts/game_night.py pick --players 5 --minutes 90 \

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.

md
python3 scripts/game_night.py pick --players 5 --minutes 90 \

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

md
python3 scripts/game_night.py pick --players 5 --minutes 90 \

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

md
python3 scripts/game_night.py pick --players 5 --minutes 90 \

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
python3 scripts/game_night.py pick --players 5 --minutes 90 \

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

md
python3 scripts/game_night.py pick --players 5 --minutes 90 \

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises executable commands that persist state to a local file (game_night.json) but does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization gap: an agent may be induced to perform file writes without clear user-visible limits, which is risky even if the intended write is only local rotation state.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The inline comment at L754 says the next picker is computed as the 'least recently picked among present people', which implies use of recent pick history. Instead, the code uses each person's index in the rotation list and selects the minimum, which is simply the earliest position in the current list and does not consult pick timestamps or pick history beyond prior list reordering. This is an active contradiction between the stated intent and the implemented logic.

Content

No source excerpt is available for this finding.