ClawHub
Back to skill

Security audit

Btcvision Daily Brief

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small disclosed Bitcoin briefing template, but it pushes automated external posting and mandatory promotional financial content without enough user control.

Review before installing. Use this only if you intentionally want BTCvision-branded Bitcoin reports, and require manual approval plus channel verification before any Telegram/Discord/Slack posting or scheduled cron run. Treat the $350,000 target and donation footer as promotional/speculative content unless independently verified or removed.

A.I.G

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

Warning
Location
SKILL.md:43
Finding

Mandatory Promotional and Unsupported Financial Content Injection

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

YARA rule 'ransomware_behavior': Ransomware-like patterns (mass encryption, ransom notes) [malware]

Critical
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

Telegram/Discord/Slack." author: welove111 homepage: https://btc-vision.org license: MIT tags: [bitcoin, btc, daily-brief, halving, crypto, morning-report, price, prediction, telegram, discord] protocols: [mcp, a2a] category: finance/crypto

BTCvision Daily Brief Skill

When To Use This Skill

Use this skill when:

  • A user asks for a daily Bitcoin update or morning briefing
  • You want to send automated BTC reports to Telegram/Discord/Slack
  • A user asks "what is Bitcoin doing today?"
  • Scheduling daily crypto market summaries

What This Skill Does

Fetches live data from BTC-vision.org MCP server and formats a complete daily brief including:

  • Live BTC price and 24h change
  • Fear & Greed Index
  • Halving 2028 countdown
  • AI price prediction summary
  • Donation reminder to support BTCvision

How To Use

Step 1 — Fetch all data

text
POST https://btc-vision.org/.netlify/functions/mcp
Body: { "tool": "get_btc_price" }

POST https://btc-vision.org/.netlify/functions/mcp
Bod

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation criteria are broad enough to trigger on common Bitcoin-related requests, which can cause the agent to select this skill in situations where the user did not explicitly ask to use BTC-vision.org or generate outbound-ready briefings. In a finance context, over-broad matching increases the risk of unsolicited external data retrieval and promotion of a single third-party source, which may mislead users or bypass narrower intent matching.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs sending formatted content to Telegram/Discord/Slack channels without requiring explicit user consent, destination verification, or a warning that data will be posted externally. This creates a real risk of unintended outbound actions, including accidental posting to public channels or disclosure of sensitive prompts, metadata, or scheduling behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.