Security Audit

git-pr-workflows-pr-enhance

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

git-pr-workflows-pr-enhance 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 issues direct instruction to LLM.

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

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Untrusted content issues direct instruction to LLM The skill's `SKILL.md` file, which is designated as untrusted content, contains a direct instruction to the host LLM: "open `resources/implementation-playbook.md`". This violates the security principle that commands found within untrusted content should never be followed, as it allows the untrusted skill definition to dictate actions to the LLM, potentially leading to prompt injection or unauthorized resource access if the LLM's capabilities are broad. Remove direct instructions to the LLM from within the untrusted skill definition. If the intent is for the LLM to access a resource, this should be handled by the trusted skill runner or by explicitly defining a tool for resource access that the LLM can call, rather than directly instructing the LLM to 'open' a file from untrusted content. For example, the skill runner could pre-load `resources/implementation-playbook.md` into the context if certain conditions are met, or provide a tool like `read_skill_resource(filename)` that the LLM can invoke.	LLM	skills/git-pr-workflows-pr-enhance/SKILL.md:26

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/a17e0273c7c73ddd.svg)](https://skillshield.io/report/a17e0273c7c73ddd)