Security audit

Firm Vs Bridge Pack

Security checks for vulnerabilities and agentic risk

Overview

This is a small VS Code bridge skill that clearly states it syncs editor context with OpenClaw Gateway, with no bundled executable code or hidden persistence found.

Install this only if you are comfortable sending selected VS Code context, file contents, diagnostics, and session metadata through OpenClaw Gateway. Avoid syncing secrets, proprietary code, or regulated data unless that use is approved for your environment.

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 (2)

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill explicitly pushes and pulls VS Code context, including selections, files, and diagnostics, to an external Gateway, but the documentation does not clearly warn users that potentially sensitive editor contents may be transmitted off-editor. In a bridge/integration skill, this omission materially increases the risk of accidental disclosure of source code, secrets, proprietary data, or diagnostic metadata because users may invoke the tools without informed consent.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: The only prominent warning in the skill documentation is written in French, while the rest of the file is in English. This imposes a language choice without opt-in or justification and may prevent some users from understanding the warning.

Static analysis

No suspicious patterns detected.