ClawHub
Back to skill

Security audit

Google Contacts Create

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Google Contacts creation helper with disclosed credential and tool requirements, but users should understand it can change their contacts account.

Install only if you intend to let the agent create Google Contacts through your Composio-backed Google access. Use a least-privileged credential where possible, confirm the contact details before invocation, and watch for duplicate contacts if a run is retried after a partial success.

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 (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The metadata declares a required COMPOSIO_API_KEY, but the skill description does not clearly warn that use of the skill depends on access to a sensitive credential tied to external account actions. This increases the risk of users or orchestrators invoking the skill without understanding the trust boundary or the consequences of granting credential-backed access.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly creates a new Google contact but the user-facing description and expected output do not warn that it will modify external user data. This can lead to uninformed or accidental execution of a state-changing action in a personal account, especially in an agent workflow where users may assume a read-only or low-impact operation.

Static analysis

No suspicious patterns detected.