ClawHub
Back to skill

Security audit

Hacker News

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Hacker News lookup helper that uses disclosed public APIs and does not request credentials, persistence, or system-changing authority.

Install this if you are comfortable with a local shell script making unauthenticated requests to Hacker News and Algolia. Review the script first in stricter environments because it depends on curl, jq, and python3 and does not declare a formal permission boundary, but the inspected behavior is purpose-aligned and non-persistent.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill exposes shell and network-backed functionality but does not declare any tool scope or permission boundaries in the skill metadata. That creates an authorization and transparency gap: an agent may invoke networked commands or shell scripts without an explicit allowlist, increasing the risk of unintended command execution, overbroad access, or misuse if the script behavior changes or is more capable than the documentation suggests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.