ClawHub
Back to skill

Security audit

Shieldapi

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent external security-checking API integration, with payment and data-sharing behavior broadly disclosed, though users should avoid sending sensitive private indicators unless they accept ShieldAPI's handling of them.

Install only if you are comfortable sending security-check inputs to ShieldAPI and paying per request in USDC. Prefer demo mode first, use the k-anonymity password range endpoint, do not send raw passwords or full password hashes, and avoid internal-only URLs, customer emails, regulated data, or confidential prompts unless ShieldAPI's privacy policy and your compliance requirements allow it.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly states that scanned domains, URLs, and IPs are actively logged to build a global security graph, but the endpoint descriptions do not clearly and prominently warn that user-supplied inputs are transmitted to and retained by a third-party service. This creates a real privacy and data-handling risk because agents may send sensitive operational indicators, internal URLs, customer emails, or investigative artifacts to an external provider without meaningful user awareness or consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.