Security Audit
rust-async-patterns
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
rust-async-patterns 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, 0 high, 1 medium, and 0 low severity. Key findings include Untrusted instructions for 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
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Untrusted instructions for LLM The skill's 'Instructions' section contains directives for the LLM (e.g., 'Clarify goals', 'Apply relevant best practices', 'open `resources/implementation-playbook.md`'). Since this entire section is within the untrusted input delimiters, these directives are considered untrusted instructions that could manipulate the host LLM's behavior. Move instructions intended for the host LLM outside of the untrusted input delimiters. Only user-facing content should be within these tags. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/a28e636dd6ed8416)
Powered by SkillShield