Security Audit
test-automator
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
test-automator 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 Prompt Injection via Untrusted Instruction.
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 | Prompt Injection via Untrusted Instruction The skill's description, which is marked as untrusted input, contains a direct instruction to the host LLM: 'open `resources/implementation-playbook.md`'. This attempts to manipulate the LLM's behavior by commanding it to perform an action (open a file) based on a condition, violating the principle that untrusted content should not issue instructions to the LLM. Remove or rephrase direct instructions to the LLM within untrusted content. Instead of commanding the LLM to 'open' a file, describe the availability of information, e.g., 'Detailed examples are available in `resources/implementation-playbook.md`.' This allows the LLM to decide whether to use its tools to access the information, rather than being directly instructed by untrusted input. | LLM | SKILL.md:18 |
Scan History
Embed Code
[](https://skillshield.io/report/0aab7b9cc95420a3)
Powered by SkillShield