Security audit

Google Calendar (via gogcli)

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Google Calendar helper that uses gogcli for calendar reads and confirms before writes, with no hidden or unrelated behavior found.

Install only if you are comfortable giving gogcli access to your Google Calendar data. Review the third-party Homebrew formula and Google authorization scope, and rely on the skill's explicit confirmation step before any calendar create, update, delete, or RSVP action.

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

System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
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)

Direct Prompt Extraction

High

Category: System Prompt Leakage
Content: Use `gog` (gogcli) for Google Calendar: agenda (events list) and keyword search across calendars. ## Output rule (tokens vs reliability) gogcli stdout should stay parseable; prefer `--plain` / `--json` and put hints to stderr. [oai_citation:0‡GitHub](https://github.com/steipete/gogcli/blob/main/AGENTS.md?utm_source=chatgpt.com)
Confidence: 85% confidence
Finding: Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Static analysis

No suspicious patterns detected.