openclaw-read-flow

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:32 PM UTC
• Version:
  1.0.0

Overview

This is a disclosed FreshRSS reading-workflow skill with no included executable code or hidden destructive behavior.

Install only if you are comfortable letting an agent read your FreshRSS unread feed. Use a FreshRSS-specific API password, review any referenced external scripts before running them, set feed or item limits for sensitive accounts, and keep read-state changes or knowledge-base writes approval-gated.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The skill explicitly instructs the agent to work in Simplified Chinese, which can override a user's preferred language and reduce usability or accessibility for users who need another language. While this is not a classic security exploit, it is a genuine policy/control issue because a skill-level instruction can improperly constrain agent behavior without user opt-in.

VirusTotal

63/63 vendors flagged this skill as clean.