Security audit

Google Workspace Automation

Security checks for vulnerabilities and agentic risk

Overview

The skill is a Google Workspace planning helper, but it can recommend overly broad Google permissions and exports untrusted CSV fields without spreadsheet-safety protections.

Review generated OAuth scopes before using this skill's plans. Prefer narrower read-only or file-specific Google scopes where possible, and avoid opening CSV exports in spreadsheet software when action names or services came from untrusted input.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: scripts/plan_workspace_automation.py:9
Finding: Overbroad OAuth Scope Recommendations Violate Least Privilege
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/plan_workspace_automation.py:57
Finding: CSV Formula Injection Through Untrusted Action Fields
Content: View full analysis
Remediation: View remediation

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: 82% confidence
Finding: The skill references bundled resources to run a Python script and read a guide, which implies file read/write-capable behavior, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates a mismatch between documented capabilities and enforced boundaries, increasing the risk that an agent may access local files without clear authorization or review constraints.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.