Security Audit
seo-content-refresher
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
seo-content-refresher 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 Skill requests file access without explicit tool definition.
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 | |
|---|---|---|---|---|
| MEDIUM | Skill requests file access without explicit tool definition The skill contains an instruction for the LLM to 'open `resources/implementation-playbook.md`'. While no explicit file reading tool is defined in the skill's manifest or supporting files, this instruction implies that the skill expects or intends the host LLM to have file system access. If the LLM environment provides default file reading capabilities, this could lead to unintended data access or exfiltration of local files, representing an excessive permission request or a potential data exfiltration vector. Explicitly define any required file access tools in the skill's manifest with the narrowest possible scope and clear user consent. If file access is not intended, remove instructions that imply such capabilities. | LLM | SKILL.md:18 |
Scan History
Embed Code
[](https://skillshield.io/report/954df91eb42666ed)
Powered by SkillShield