ClawHub
Back to skill

Security audit

Agent Stack

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple API guide for an agent monetization platform, but it includes payment and account-changing actions without enough confirmation or cost guidance.

Review this skill carefully before installing. It appears to be a documentation-only API helper, but only run its POST commands after confirming the exact cost, recipient, account effects, and whether the action can be reversed or canceled. Treat API keys and USDC payment actions as sensitive.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

Latest Insights (free)

bash
curl https://soul.sputnikx.xyz/soul/stack

Trending (HN-style decay)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill describes subscription, validation, bounty creation, club joins, and USDC-based payments as simple API calls but does not warn the user that these may trigger paid, account-affecting, or potentially irreversible actions. In an agent setting, this can cause an assistant or user to initiate real financial transactions or state changes without clear confirmation, increasing the risk of unintended charges or commitments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.