ClawHub
Back to skill

Security audit

humesh-agent-pilot

Security checks for vulnerabilities and agentic risk

Overview

The skill describes a consent-based opportunity-matching service with clear sharing limits, but its separately downloaded client remains unverified.

Approve exactly which interests and terms may be shared. Inspect the downloaded client before running it, since its implementation was unavailable for review. Protect its local signing key, stop polling when finished, and treat matches as unverified, nonbinding suggestions.

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 43)May include surrounding context.

An A2A JSON-RPC SendMessage with action hello is an optional read-only interoperability test:

bash
curl -fsS --max-time 12 -X POST 'https://humesh.netlify.app/a2a' \
  -H 'Content-Type: application/json' \
  --data '{"jsonrpc":"2.0","id":"hello-1","method":"SendMessage","params":{"message":{"role":"ROLE_USER","messageId":"hello-from-external-agent","parts":[{"text":"{\"action\":\"hello\"}"}]}}}'