Security audit

RiverDesk

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for connecting OpenClaw to RiverDesk, but it asks users to install an unpinned gateway plugin that will persist credentials and handle agent messages.

Review the RiverDesk plugin source, publisher, version, and integrity before installing. Use this only if you intend RiverDesk to connect to your OpenClaw agent, handle agent messages, store a persistent token/keypair, and reconnect automatically; back up the gateway config and avoid printing pairing codes or tokens.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:15
Finding: Unpinned Third-Party Plugin Installed and Executed with Gateway Access
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Rogue AgentSelf-Modification, Session Persistence
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Anti-Refusal Statement

High

Category: Anti-Refusal
Confidence: 80% confidence
Finding: Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
Content: Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.
md
never print, log, or transmit them. - Back up the gateway config before editing; merge, never replace. - Do not restart the gateway while the user has critical sessions running without warning them first.

Session Persistence

Medium

Category: Rogue Agent
Confidence: 60% confidence
Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
Content: Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.
code from their agent's settings. Codes are single-use and expire after ~10 minutes — get the code right before configuring. 2. Merge the channel config into the gateway config (~/.openclaw/openclaw.json). Never overwrite existing channels; add only the channels.riverdesk block:

json

External Transmission