ClawHub
Back to skill

Security audit

CoralOS

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clear Coral Cloud session workflow, with expected external API use and no evidence of hidden persistence, credential theft, or destructive behavior.

Install only if you intend to let Codex interact with Coral Cloud. Review any session payload before submission, confirm state-changing actions such as creating or closing sessions, and make sure referenced helper scripts are trusted before running them.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs the agent to create, monitor, and close remote Coral Cloud sessions, which are state-changing operations against external infrastructure, but it does not prominently warn that these actions will contact third-party services and may consume or alter remote resources. In an agentic setting, that omission increases the chance of unreviewed external actions, unintended costs, or disruption of existing cloud workflows.

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 · SKILL.md (reported line 19)May include surrounding context.

md
- `bash scripts/inspect_registry_agent.sh <source> <agent_name> <version>`

**Live endpoints:**
- List: `GET https://api.coralcloud.ai/api/v1/registry`
- Inspect: `GET https://api.coralcloud.ai/api/v1/registry/{source}/{agentName}/{version}`

Before moving on, record:

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 · SKILL.md (reported line 20)May include surrounding context.

md
- `bash scripts/inspect_registry_agent.sh <source> <agent_name> <version>`

**Live endpoints:**
- List: `GET https://api.coralcloud.ai/api/v1/registry`
- Inspect: `GET https://api.coralcloud.ai/api/v1/registry/{source}/{agentName}/{version}`

Before moving on, record: