Clawtrix Saas Intel

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:32 PM UTC
• Version:
  0.2.0

Overview

This instruction-only skill recommends SaaS-related ClawHub skills and saves a local report, with the main caveat that it reads agent context and writes that context-derived report to memory.

Before installing, confirm you are comfortable with the agent reading SOUL.md, querying ClawHub, and saving a local recommendation report under memory/reports. Review any recommended billing, auth, or customer-data skills separately before installing them, because those downstream skills may carry higher risk than this discovery skill.

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)

Missing User Warnings

Low

• Confidence: 89% confidence
• Finding: The skill instructs the agent to write a discovery report to `memory/reports/...` during routine operation without an explicit user-facing notice or consent step. Even though the content appears operational rather than overtly sensitive, it may include derived information from `SOUL.md` such as product domain, installed skills, business model, and stack details, creating persistence of potentially sensitive internal metadata.

VirusTotal

61/61 vendors flagged this skill as clean.