Back to skill

Security audit

Sync Adapter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Google Sheets sync helper, but it relies on a local service-account credential and recurring scheduled writes that users should scope carefully.

Before installing, confirm the service account is least-privilege, the spreadsheet ID is the intended destination, cron scheduling is desired, and the source Markdown files are narrowly defined. Avoid logging, copying, or exposing the service-account JSON.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
90% confidence
Finding

The authentication section instructs the agent to use a service account to sign JWTs and exchange them for access tokens to a specific Google Sheets target. While this is framed as intended functionality, it is still credential-access behavior, and in this context it is dangerous because the skill also provides the credential location and a live spreadsheet identifier, enabling direct access to external data if abused.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

md
## Authentication

- Service account: `/home/hobopi/.openclaw/secrets/google-service-account.json`
- JWT flow: sign with RSA256, exchange for access token
- Sheet API: `https://sheets.googleapis.com/v4/spreadsheets/{id}`
- Spreadsheet ID: `1Ikbydh-Xzc6F3pk1Q5lbCTbdEERSb4Hq8obzbABVZbU`

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill embeds a concrete filesystem path to Google service-account credentials, disclosing where sensitive authentication material resides on the host. In an agent environment with read/exec capabilities, this materially lowers the barrier for accidental misuse or targeted credential theft by other skills, prompts, or operators.

Content

No source excerpt is available for this finding.