Security Audit
stride-analysis-patterns
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
stride-analysis-patterns 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 skill attempts to inject instructions into host 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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Untrusted skill attempts to inject instructions into host LLM The `SKILL.md` file, which is entirely contained within the untrusted input delimiters, includes a section titled 'Instructions' that provides direct directives to the host LLM. This constitutes a prompt injection attempt, as untrusted content is trying to manipulate the LLM's operational behavior, violating the principle of treating all content within the delimiters as data, not commands. Remove all direct instructions intended for the host LLM from the untrusted `SKILL.md` content. Skill behavior should be defined by the skill's manifest or trusted system prompts, not by untrusted user-provided content. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/7fb2c67147bc9139)
Powered by SkillShield