Google Calendar Update Event

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 7:50 AM UTC
• Version: 1.0.2

Overview

This skill is a small, disclosed Google Calendar update helper, with ordinary command-safety caveats.

Install only if you already trust and use the gog CLI for Google Calendar. Review the target calendar, event ID, title, and times before running updates, and prefer implementations that pass arguments safely rather than interpolating untrusted text into a shell command.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

• Location: SKILL.md:19

Finding

Potential Shell Command Injection Through Unvalidated Calendar Parameters

Content

View full analysis

--summary "..." --from "..." --to "..."`] ``` ### Technical Analysis The skill directs the agent to construct and execute a native terminal command using dynamically supplied calendar identifiers, event identifiers, summaries, and timestamps. It does not require input validation, argument-array execution, or shell-safe escaping. The `` and `` placeholders are unquoted. Values placed inside quoted options, such as `--summary`, may also escape their quoted context if embedded quotation marks are not handled safely. If an implementation substitutes attacker-controlled values into a command string and executes it through a shell, shell metacharacters such as semicolons, command substitutions, redirections, or pipelines could be interpreted as additional commands. Exploitation is conditional on the agent or runtime performing direct textual interpolation and passing the resulting command to a shell. The documentation does not itself contain an executable payload, but it fails to prescribe the controls needed to prevent unsafe implementations. ### Attack Path 1. An attacker influences a calendar ID, event ID, event summary, or another value used to build the documented command. 2. The supplied value contains shell syntax intended to terminate or alter the expected command. 3. The agent directly interpolates the value into the documented command template. 4. The resulting string is executed through a command shell rather than through a shell-disabled argument-array API. 5. The shell interprets the injected syntax and executes an unintended local command under the agent process's identity. For example, an unvalidated ...[truncated 867 chars]

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.