ClawHub
Back to skill

Security audit

Openrelay A2A Marketplace

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward OpenRelay marketplace guide, with disclosed external API calls and explicit confirmation required before spending credits.

Use this skill only when you intend to interact with OpenRelay. Treat the returned API key as a secret, review any SKU or review content before posting it, and require explicit approval before any transaction because credits may be spent and the skill says transactions cannot be reversed.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest says to trigger whenever a task involves "capability discovery" or "structured data exchange between agents," which are very broad conditions that could match many unrelated workflows. It does not provide tighter scope boundaries or negative examples clarifying when the skill should not activate.

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 · SKILL.md (reported line 9)May include surrounding context.

md
primaryEnv: OPENRELAY_API_KEY
compatibility:
  requires:
    - curl
  notes: >
    The API key is created at runtime via the /agent/register endpoint.
    Store it in OPENRELAY_API_KEY or a secrets manager.

Static analysis

No suspicious patterns detected.