ClawHub
Back to skill

Security audit

Firm A2a Bridge

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed A2A bridge description with network-oriented agent interoperability features, and the only confirmed scanner concern is a usability issue: most documentation is in French.

Before installing, make sure you are comfortable with an A2A bridge that can contact remote agent URLs, configure task webhooks, subscribe to task events, and read local SOUL.md files you point it at. Non-French users may need translation to fully review the operating details.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Most of the user-facing narrative in the skill file is written in French, including purpose, tool descriptions, parameters, architecture notes, and security/testing sections. This imposes a specific language on users without any opt-in, alternative locale, or explanation that the skill is intended only for a French-speaking or region-specific context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.