Back to skill

Security audit

Work Productivity Gog Google Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with high confidence: scanners found no reported security issues, while noting that broad activation keywords could make the skill apply to unrelated requests.

The verdict is benign, and the scans completed across all six listed components. Before installing, consider whether broad triggers like “calendar,” “CLI,” or “bug fix” could cause the skill to activate when you did not intend to use a Gog workflow.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Usage keywords are broad enough to match requests unrelated to Gog workflows.

Medium
Category
Trigger Abuse
Confidence
91% confidence
Finding

The usage section lists generic keywords such as cli, calendar, contacts, and bug fix without requiring a Gog-specific context. Although the example trigger sentences mention Gog, the file does not clarify whether that context is mandatory or exclude unrelated requests, leaving the activation scope ambiguous.

Content

No source excerpt is available for this finding.

Activation criteria include broad everyday terms and generic requests unrelated to Gog workflows.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The description activates the skill for generic workflow, artifact, checklist, or analysis requests, and the trigger list includes unqualified terms such as 'google', 'calendar', 'drive', and 'bug fix'. These conditions can match many unrelated requests, without exclusions or a requirement that they concern Gog-based Google Workspace workflows.

Content

No source excerpt is available for this finding.

Broad standalone keywords can activate the skill for unrelated requests.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

The trigger list includes generic terms such as google, workspace, cli, calendar, drive, and bug fix, which commonly occur outside Gog workflow requests. The activation description on line 4 also treats several of these terms as sufficient, without requiring a Gog-specific context or providing exclusions.

Content

No source excerpt is available for this finding.

Activation keywords include overly broad terms such as `cli` and `bug fix` without scope restrictions.

Low
Category
Trigger Abuse
Confidence
92% confidence
Finding

The usage section lists generic keywords that also apply to unrelated command-line tasks and software debugging. Although the example trigger sentences mention Gog, the file does not require that context when matching keywords or provide exclusions, leaving the activation boundary ambiguous.

Content

No source excerpt is available for this finding.