Security Audit
wiki-page-writer
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
wiki-page-writer 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 broad filesystem read access.
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 broad filesystem read access The skill explicitly instructs the agent to 'Read all relevant files' and 'TRACE ACTUAL CODE PATHS' to generate documentation. While necessary for its function, this implies a broad scope of filesystem access. If the host environment does not adequately sandbox or restrict the definition of 'relevant files', this could lead to the agent accessing and processing sensitive information outside the intended project scope. Ensure the host LLM's file system access tools are strictly sandboxed to the project directory or explicitly defined safe paths. Implement granular access controls to prevent the agent from reading files outside its intended operational scope. Clarify or restrict the definition of 'relevant files' within the skill's instructions if possible. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/4499392a44c79760)
Powered by SkillShield