ClawHub
Back to skill

Security audit

Geospatial Osint

Security checks for vulnerabilities and agentic risk

Overview

The skill is a geospatial OSINT dashboard guide, but it under-scopes privacy and safety controls for CCTV aggregation and automated military/geopolitical monitoring.

Review this skill carefully before installing or using it. It is documentation-only, but it is aimed at building dashboards that aggregate sensitive public-location intelligence. Use only lawful, authorized data sources, avoid exposed private camera feeds unless you have clear rights to use them, and add explicit user approval, logging, rate limits, and source/region restrictions before implementing automated monitoring or alerts.

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/adsb-api.md (reported line 10)May include surrounding context.

md
## Authentication

1. Register at https://www.adsbexchange.com/
2. Get API key from account page
3. Include in header: `Authorization: Bearer YOUR_API_KEY`

## Endpoints

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly promotes collecting and overlaying public CCTV camera feeds via Insecam without any privacy, legality, or ethical-use warning. Even if the feeds are publicly reachable, aggregating them into an OSINT dashboard lowers barriers to surveillance, stalking, or location monitoring and increases misuse risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The region monitoring section operationalizes automated geopolitical surveillance and anomaly alerting for named sensitive regions, including military activity, without any caution about legal, ethical, or escalation risks. In context, this materially assists persistent intelligence monitoring workflows that could be repurposed for harmful targeting or sensitive surveillance.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · references/satellite-passes.md (reported line 59)May include surrounding context.

md
| Provider | API | Cost |
|----------|-----|------|
| Planet Labs | https://api.planet.com/ | Pay-per-scene |
| Maxar | https://developer.maxar.com/ | Enterprise |
| Capella | https://www.capellaspace.com/ | Pay-per-scene |
| Airbus | https://www.airbus.com/ | Contact sales |

Static analysis

No suspicious patterns detected.