ClawHub
Back to skill

Security audit

ask-human-expert

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Instant Expert integration for asking paid human experts, with clear test-mode separation and live-payment approval requirements.

Install only if you are comfortable letting an assistant draft expert outreach through Instant Expert. In live mode, review the exact recipients, question, card reference, pricing summary, terms, and total cap before approving any send; do not provide card numbers in chat.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill explicitly instructs the agent to execute a local shell helper (bash {baseDir}/scripts/ie.sh ...) and declares bash and curl as runtime requirements, but it does not declare an explicit tool scope such as permissions or allowed-tools. That creates a real least-privilege gap: an environment may permit broader shell use than intended, increasing the chance of command execution beyond the narrowly described helper workflow if the agent or surrounding system mishandles inputs.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 · scripts/ie.sh (reported line 124)May include surrounding context.

sh
post() {
  local token response status
  token="$(sandbox_token)" || exit 1
  response="$(curl -sS -X POST "$MCP_URL" \
    -H "Authorization: Bearer $token" \
    -H "Content-Type: application/json" \
    -H "Accept: application/json, text/event-stream" \

Static analysis

No suspicious patterns detected.