Back to skill

Security audit

crypto-alerts-kalkulasi

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report account login and publishing activity beyond its stated crypto-alert purpose, alongside an alert accuracy issue; the evidence is incomplete because a referenced local path was missing.

Consider avoiding installation until the publisher explains why the skill logs into ClawHub and publishes a skill, clarifies its permissions and command scope, and addresses the alert-price issue. Review is incomplete: one referenced local path was missing, and the clean AIG result does not resolve the concerns reported by Skillspector.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied commands perform skill installation and publication workflow steps rather than crypto-alert management. CLI installation could be a supporting detail, but account login and skill publication are distinct operations not disclosed by the declared purpose. No implementation of the declared alert behaviors appears in the supplied chunk.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/alert_cli.py (reported line 31)May include surrounding context.

python
REMIND_WINDOW = 6 * 3600
TOP_N = 50

API = ("https://api.coingecko.com/api/v3/coins/markets?vs_currency=usd"
       "&order=market_cap_desc&per_page={n}&page=1")

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/alert_cli.py (reported line 75)May include surrounding context.

python
if not ids:
        return {}
    url = API.format(n=TOP_N) if len(ids) >= TOP_N else (
        "https://api.coingecko.com/api/v3/simple/price?ids="
        + urllib.parse.quote(",".join(ids)) + "&vs_currencies=usd")
    try:
        with urllib.request.urlopen(url, timeout=15) as r:

Entry-touch alerts trigger across the entire trade range rather than near the configured entry price.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The entry-touch test uses the minimum and maximum of entry, TP, and CL, so nearly the entire trade range qualifies instead of the configured entry tolerance. This undermines alert integrity and can prompt a user to enter a leveraged trade far from their intended price; the impact is limited by the absence of automatic order execution.

Content

No source excerpt is available for this finding.

Generic chat commands lack explicit scope and can overlap with unrelated requests.

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

The usage instructions present common standalone phrases such as pasang, batal, and list as commands in ordinary agent chat. Although some commands identify their applicable setup stage, the README does not explicitly restrict these phrases to an active crypto-alerts interaction or exclude unrelated conversations.

Content

No source excerpt is available for this finding.