Security Audit
hig-components-search
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
hig-components-search 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, 1 high, 0 medium, and 0 low severity. Key findings include Untrusted content attempts to instruct LLM behavior.
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 | |
|---|---|---|---|---|
| HIGH | Untrusted content attempts to instruct LLM behavior The skill's `SKILL.md` file, which is marked as untrusted input, contains explicit instructions intended for the host LLM. This is a prompt injection attempt, as untrusted content should not dictate the LLM's operational logic or information retrieval strategy. The instruction 'Check for `.claude/apple-design-context.md` before asking questions. Use existing context and only ask for information not already covered.' attempts to guide the LLM's internal process. Remove direct instructions to the LLM from untrusted content. If this guidance is necessary for the skill's operation, it should be incorporated into the trusted system prompt or skill definition outside the untrusted input block. | LLM | SKILL.md:5 |
Scan History
Embed Code
[](https://skillshield.io/report/376fcc22e16a9923)
Powered by SkillShield