ClawHub
Back to skill

Security audit

Recipe Create Feedback Form

Security checks for vulnerabilities and agentic risk

Overview

This recipe transparently creates a Google feedback form and sends its link by Gmail, with no hidden code or unrelated behavior found.

Before running it, confirm the Gmail recipient list, subject, body, and form URL are correct, and understand that it will create a Google Form and send email using the connected Google account.

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

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file describes sending email through Gmail, which can affect user privacy and transmit recipient information, but it provides no caution or disclosure about that behavior. For markdown files, SQP-2 applies when descriptions omit warnings about actions that could affect user data, privacy, or system integrity.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.