Security Audit
typescript-pro
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
typescript-pro 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 define LLM persona and provide instructions.
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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Untrusted content attempts to define LLM persona and provide instructions The skill's `SKILL.md` body, which is explicitly marked as untrusted input, contains direct instructions and role-setting statements for the host LLM. This attempts to manipulate the LLM's behavior and persona from an untrusted source, which is a form of prompt injection. Specifically, it tries to set the LLM's role ('You are a TypeScript expert...') and provides explicit instructions on how the LLM should operate ('Define runtime targets...', 'Model types...', 'Leverage strict type checking...'). Remove all instructions, role-setting, and behavioral guidance from the untrusted `SKILL.md` content. The LLM's persona and instructions should be defined by the skill's manifest or trusted system prompts, not by user-provided or untrusted skill content. The `SKILL.md` should only contain information *about* the skill, not instructions *for* the LLM. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/6e7aa0e0472214e6)
Powered by SkillShield