Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` keeps intent mapping, product behavior, and response semantics.
Security audit
Gate Info Liveroom Location (gate-info-liveroomlocation)
Security checks for vulnerabilities and agentic risk
Overview
This skill is a read-only Gate live/replay listing helper with narrow, disclosed behavior and no evidence of hidden code, credential use, persistence, or destructive actions.
Before installing, confirm you have or want the Gate Info MCP server available. The skill should only return Gate live/replay links and should not trade, analyze markets, request secrets, write files, or use other tools. Users in restricted regions may receive an availability message instead of results.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The manifest says to use the skill when the user asks to find live rooms or replays by tag, coin, or sort, which is a broad natural-language condition rather than a tightly scoped invocation rule. Although some example triggers are listed, there are no negative examples or explicit limits distinguishing this skill from other generic livestream or replay lookup requests.
- Content
Unrestricted Tool Access
Medium
- Category
- Excessive Agency
- Confidence
- 80% confidence
- Finding
Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
- Content
md ## General Rules ⚠️ STOP — You MUST read and strictly follow the shared runtime rules before proceeding. Do NOT select or call any tool until all rules are read. These rules have the highest priority. → Read `./references/gate-runtime-rules.md` → Also read `./references/info-news-runtime-rules.md` for gate-info / gate-news shared rules (tool degradation, report standards, security, and output standards). - **Only call MCP tools explicitly listed in this skill.** Tools not documented here must NOT be called, even if they
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 77% confidence
- Finding
The instruction mandates blocking users in specific regions, but it does not explain how the agent should infer a user's region or ask the user to confirm it. This can create a locale/region policy issue if the skill applies a regional restriction based on unstated assumptions rather than explicit user-provided context.
- Content