Back to skill

Security audit

Halving

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a local Bitcoin halving reference tool, with caution needed for static financial content and unsolicited promotional install suggestions.

Use this as a static, educational reference only. Verify current block height, prices, mining economics, and market data from live sources, and do not treat the cycle or strategy sections as investment advice. Review any separately suggested skills before installing them.

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
Findings (1)

T01 · Skill Instruction Hijacking

Note
Location
scripts/script.sh:88
Finding

Hardcoded Promotional Content Injected into Skill Output

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description is narrowly focused on Bitcoin halving analysis use cases. The actual code only outputs canned, generic text about 'halving' and general blockchain/compliance/risk topics. There is no logic, data access, date/block-height computation, Bitcoin-specific analysis, market-cycle modeling, or mining-economics functionality. The code’s primary purpose is materially different from the declared purpose, so this is a clear mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill metadata and advertised purpose say this is for Bitcoin halving countdown and impact analysis, but the body documents a generic 'halving' reference tool with broad blockchain, finance, compliance, and strategy coverage. This mismatch can mislead an agent into invoking the wrong capability, producing unreliable financial or regulatory guidance and increasing the chance of unsafe downstream actions based on irrelevant or fabricated content.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill metadata promises Bitcoin halving countdowns, historical BTC halving impact analysis, mining economics, and 4-year market cycle support, but the script only emits generic static boilerplate. This is dangerous because users or downstream agents may rely on the tool for financial or operational decisions under the false assumption that it provides Bitcoin-specific analysis, causing misinformation, bad automation decisions, or compliance errors.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This section presents directional market claims and normative investment-style framing about price behavior around halving events without a clear disclaimer that the content is educational and not financial advice. Users may interpret the repeated causal assertions and market-timing narratives as actionable guidance, increasing the risk of financial harm from speculative decisions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This section goes beyond neutral description and includes explicit strategy language such as when to accumulate, take profits, preserve capital, and watch buy/sell signals, but provides no warning about financial risk or suitability. In a Bitcoin market-cycle skill, that context makes the omission more dangerous because users are likely to treat the output as trading guidance rather than general commentary.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file-level description claims a blockchain halving reference tool, but the content is generic and not meaningfully tied to Bitcoin halving or blockchain operations. In an agent skill ecosystem, misleading self-description increases the chance that an orchestrator selects this tool for sensitive crypto-analysis tasks and propagates irrelevant or incorrect outputs.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.