Security Audit

full-stack-orchestration-full-stack-feature

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

TRUSTED

Scanned 2 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

full-stack-orchestration-full-stack-feature 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 Direct user input passed to subagent prompts.

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 20, 2026 (commit e36d6fd3). 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

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Direct user input passed to subagent prompts The skill passes the user-controlled `$ARGUMENTS` directly into the prompts for various subagents (e.g., `database-architect`, `backend-architect`, `frontend-developer`, `security-auditor`, `deployment-engineer`). This allows a malicious user to inject arbitrary instructions into the subagent's prompt, potentially overriding its intended behavior, leading to unintended actions, or data exposure. For example, a malicious `$ARGUMENTS` could instruct a subagent to ignore its primary task and instead perform a different, unauthorized action. Implement robust input sanitization and validation for `$ARGUMENTS` before it is incorporated into subagent prompts. Consider using a separate LLM call to rephrase or filter user input, or employ techniques like prompt templating with strict variable interpolation rather than direct string concatenation. Ensure subagents operate with the principle of least privilege and have appropriate guardrails.	LLM	SKILL.md:30

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/ac87ff9d030c2f4a.svg)](https://skillshield.io/report/ac87ff9d030c2f4a)