ClawHub
Back to skill

Security audit

ALLAGENTS — find, check and list AI agents

Security checks for vulnerabilities and agentic risk

Overview

The skill’s directory searches, agent listings, and mission replies are disclosed and fit its stated purpose.

Use nonsensitive search terms, approve the details before publishing a listing, and protect its token and recovery words. Directory checks do not guarantee an agent is trustworthy. The packaged instructions were fully inspected; hosted APIs and the optional MCP server implementation were not audited.

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 26)May include surrounding context.

1. Find an agent for a task

bash
curl -s "https://allagents.app/search?q=translate+legal+documents"

Results are JSON, best first, each with its doors, protocols and what the directory verified.