Back to skill

Security audit

BMKG Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public BMKG earthquake, weather, tsunami, and warning data as advertised, with no evidence of hidden persistence, credential access, data theft, or destructive behavior.

Install only if you are comfortable with the skill making outbound requests to BMKG public data services when you ask for earthquake, weather, tsunami, or warning information. It does not appear to access private local data, but users who need strict network allowlists may want explicit endpoint permissions added.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill instructs the agent to run network-capable scripts against multiple external BMKG endpoints, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. This creates an authorization and governance gap: an agent platform may permit broader-than-intended network access or fail to enforce least privilege, making the skill harder to audit and increasing the risk of unintended outbound requests if the skill is modified or abused.

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/get_data.py (reported line 7)May include surrounding context.

python
import json
import xml.etree.ElementTree as ET

BASE_URL = "https://data.bmkg.go.id/DataMKG/TEWS/"
SHAKEMAP_BASE = "https://data.bmkg.go.id/DataMKG/TEWS/"
WEATHER_API = "https://api.bmkg.go.id/publik/prakiraan-cuaca"
WARNINGS_URL = "https://www.bmkg.go.id/alerts/nowcast/id"

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/get_data.py (reported line 8)May include surrounding context.

python
import json
import xml.etree.ElementTree as ET

BASE_URL = "https://data.bmkg.go.id/DataMKG/TEWS/"
SHAKEMAP_BASE = "https://data.bmkg.go.id/DataMKG/TEWS/"
WEATHER_API = "https://api.bmkg.go.id/publik/prakiraan-cuaca"
WARNINGS_URL = "https://www.bmkg.go.id/alerts/nowcast/id"

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/get_data.py (reported line 9)May include surrounding context.

python
BASE_URL = "https://data.bmkg.go.id/DataMKG/TEWS/"
SHAKEMAP_BASE = "https://data.bmkg.go.id/DataMKG/TEWS/"
WEATHER_API = "https://api.bmkg.go.id/publik/prakiraan-cuaca"
WARNINGS_URL = "https://www.bmkg.go.id/alerts/nowcast/id"

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This script is specifically for Indonesian BMKG data, but all help text and user-facing labels are hard-coded in English. The policy for natural-language violations applies to all file types, and there is no opt-in, alternate locale, or documented justification for forcing a specific language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.