Security Audit

Sounder25/Google-Antigravity-Skills-Library:07_deterministic_planner

github.com/Sounder25/Google-Antigravity-Skills-Library

AI SkillCommit 09376edc64e9

TRUSTED

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

Sounder25/Google-Antigravity-Skills-Library:07_deterministic_planner received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include User-controlled output path may lead to arbitrary file write.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 28, 2026 (commit 09376edc). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	User-controlled output path may lead to arbitrary file write The skill's `--output` parameter, as described in `SKILL.md`, allows users to specify an arbitrary file path for the `PLAN.json` output. Without proper sanitization and validation in the `init_plan.ps1` script (which is not provided), this could lead to an arbitrary file write vulnerability. An attacker could exploit this to write the `PLAN.json` content to sensitive system locations (e.g., configuration files, startup scripts), overwrite existing files, or perform path traversal attacks. This could potentially result in denial of service, privilege escalation, or command execution if the written file is subsequently processed or executed by the system. The `init_plan.ps1` script must implement robust validation and sanitization for the `--output` parameter. This includes: 1. Restricting output paths to a designated, non-sensitive, and ideally sandboxed directory. 2. Preventing path traversal sequences (e.g., `../`, `..\`). 3. Ensuring the path is properly quoted and escaped if it is used in any shell commands to prevent command injection. 4. Consider using a file picker or a more controlled mechanism for output location if arbitrary paths are not strictly necessary.	LLM	SKILL.md:20

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/b55b1d7e52351a44.svg)](https://skillshield.io/report/b55b1d7e52351a44)