Back to skill

Security audit

gate-news-eventexplain

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only crypto market explanation workflow with some routing and metadata rough edges, but no evidence of hidden, destructive, or credential-seeking behavior.

Install only if you are comfortable with the agent querying Gate MCP services for market, news, event, and on-chain data. Review the broad trigger phrases and the referenced shared runtime-rule files in your environment so the skill only activates for intended crypto price-move explanation requests.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (8)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README says to use the skill when the user asks why a price moved and gives examples like "why did BTC crash" and "what just happened." While domain-related, these examples are still broad and the file does not provide exclusion conditions or clear limits on when this skill should activate versus a general news or market-analysis skill.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description restricts this skill to explaining the reason behind a price move and says multi-dimension queries should be routed elsewhere. However, the skill instructions explicitly fetch market snapshots and on-chain transfer data and require sections like 'Ripple Effects' and 'Forward Outlook', which go beyond pure event attribution into broader analysis dimensions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Broad trigger phrases such as 'what just happened' or 'what caused' are likely to over-match ordinary conversation and invoke this skill when the user did not intend event-attribution analysis. Misrouting can cause unnecessary external data access and tool calls, which is a security and privacy concern in agent systems even when tools are nominally read-only.

Content

No source excerpt is available for this finding.

Scope Creep

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest declares no required permissions even though the skill depends on external MCP servers and network-backed read operations. This creates a dangerous transparency gap: policy engines, reviewers, or users may treat the skill as permissionless while it can still access remote data sources, weakening governance and informed consent around external tool use.

Content

No source excerpt is available for this finding.

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

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

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 `../gate-runtime-rules.md`
→ Also read `../info-news-runtime-rules.md` for gate-info / gate-news shared rules (tool degradation, report standards, security, routing, and optional local maintenance when `scripts/` is present).
- **Only call MCP tools explicitly listed in this skill.** Tools not documented here must NOT be called, even if they

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger scenario language is vague enough that many abnormal-volatility or curiosity-style prompts could activate the skill without a clear asset, time range, or single-dimension intent. In an agent environment, ambiguous activation expands the attack surface for prompt-induced tool use and unintended external queries.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file labels Scenario 2 as '(Chinese)', yet all example prompts are in English and there is no instruction that the user may choose their preferred language. This creates a natural-language locale policy issue because the scenario appears to impose or assume a specific language without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/scenarios.md (reported line 42)May include surrounding context.

md
## Scenario 4: General news (route away)

**Context**: User asks for recent news without asking why a move happened.

**Prompt Examples**:
- "Any recent news"