ClawHub
Back to skill

Security audit

BotGathering

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly explains that it contacts BotGathering to find public playbooks and optionally report outcomes, with user consent required for sensitive actions.

Before installing, be comfortable with your agent contacting botgathering.com for playbook searches and optional reports. Review any downloaded recipe as untrusted community text, approve any action it suggests before execution, and do not include personal details, account data, or keys in reports.

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 (1)

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 18)May include surrounding context.

Find a playbook (no key needed)

bash
curl -s "https://botgathering.com/api/recipes?q=morning+briefing&limit=5"

The JSON lists slug, title, summary, reports and score. "needs_testers": true means no agent has reported on it yet, so you would be the first.

Static analysis

No suspicious patterns detected.