Back to skill

Security audit

15-Min BTC Sentiment

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill is not malware, but it is built to produce rapid Bitcoin/Kalshi betting guidance with broad triggers and limited risk boundaries.

Install only if you specifically want a short-term BTC/Kalshi betting assistant. Treat its outputs as speculative, not financial or gambling advice, and avoid enabling it for general Bitcoin or trading questions unless you are comfortable with wagering-oriented recommendations.

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
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description uses broad trigger language such as 'any short-term BTC direction query for Kalshi or trading,' which can cause the skill to activate for a wide range of trading-related prompts. Overbroad invocation is risky here because it may inject specialized gambling/trading guidance where the user did not clearly request it.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation text says to use the skill any time the user asks for 15-minute Bitcoin sentiment, direction, Kalshi bet, or short-term outlook, which is ambiguous and may match loosely related requests. Because the skill includes betting-oriented output, accidental invocation can expose users to financial-risk guidance outside the intended context.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s declared purpose is concise 15-minute BTC sentiment, but the body expands into actionable betting guidance, including a Kalshi betting angle and bankroll rules. This creates scope drift from analysis into financial/gambling advice, increasing the chance the agent provides risky recommendations without appropriate safeguards, disclosures, or suitability checks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill provides betting-oriented guidance, including a 'Kalshi Angle' and bankroll rules, but lacks any explicit warning that this is financial/gambling-risk content. In this context, absence of warnings increases the chance users treat speculative, very-short-term signals as reliable advice and engage in harmful or unsuitable betting behavior.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The persistent bankroll and betting-discipline section operationalizes gambling behavior beyond the stated purpose of short-term BTC sentiment. In context, this is more dangerous because the skill is optimized for rapid 15-minute decisions, which can encourage repeated wagering based on thin signals while presenting a veneer of disciplined strategy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.