Security Audit

hig-technologies

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

hig-technologies 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 Untrusted content attempts to instruct LLM to check for a file and modify behavior.

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

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Untrusted content attempts to instruct LLM to check for a file and modify behavior The skill's `SKILL.md` file, which is treated as untrusted input, contains direct instructions to the host LLM. Specifically, the line 'Check for `.claude/apple-design-context.md` before asking questions. Use existing context and only ask for information not already covered.' attempts to manipulate the LLM's internal process by instructing it to look for a specific file and to alter its conversational strategy. This is a direct prompt injection, as it tries to make the LLM perform actions and modify its behavior based on untrusted content. Remove direct instructions to the LLM from untrusted skill content. Skill behavior should be defined by the manifest and skill code, not by instructions embedded in content intended for user consumption or as data. If the skill needs to access specific files, this should be handled through explicit tool calls or a defined skill execution environment, not via LLM instructions.	LLM	SKILL.md:3

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/8a280c449ee9ed1c.svg)](https://skillshield.io/report/8a280c449ee9ed1c)