Security Audit

backend-development-feature-development

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

backend-development-feature-development received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Prompt Injection via Dynamic Prompt Construction for Subagents.

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

70%

Behavioral Risk Signals

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Prompt Injection via Dynamic Prompt Construction for Subagents The skill constructs prompts for various subagents (e.g., 'business-analytics::business-analyst', 'security-scanning::security-auditor', 'backend-architect') using dynamic content derived from user input ('$ARGUMENTS') and outputs from previous subagent steps (e.g., '[include business analysis from step 1]'). If '$ARGUMENTS' or the output from an earlier subagent contains malicious instructions, these can be injected into the subsequent subagent's prompt. This could lead to the subagent deviating from its intended task, performing unauthorized actions (especially concerning high-privilege subagents like 'security-scanning::security-auditor'), or exfiltrating sensitive information. Implement robust input sanitization and validation for '$ARGUMENTS' and all intermediate outputs before they are used to construct prompts for subagents. Consider using structured outputs (e.g., JSON schema validation) for subagent responses to prevent arbitrary text from being re-injected. Employ prompt templating libraries that offer better separation of instructions and dynamic data. Implement guardrails or content moderation on subagent inputs/outputs. For high-privilege subagents like 'security-scanning::security-auditor', ensure strict sandboxing and least-privilege access controls are in place, and consider human-in-the-loop approval for sensitive operations.	LLM	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/2f19c68ad5e00b6a.svg)](https://skillshield.io/report/2f19c68ad5e00b6a)