Security Audit
git-pr-workflows-onboard
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
git-pr-workflows-onboard 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 Potential File System Access via 'open' 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 | |
|---|---|---|---|---|
| MEDIUM | Potential File System Access via 'open' instruction The skill instructs the host LLM to 'open `resources/implementation-playbook.md`'. This implies the LLM has a tool or capability to access the file system. If this 'open' tool is not properly sandboxed (e.g., restricted to the skill's directory, read-only access), it could lead to excessive permissions, allowing the LLM to read arbitrary files on the system. This could potentially be leveraged for data exfiltration if sensitive files are accessed. Ensure the LLM's file access tool is strictly sandboxed to the skill's intended files/directories and only provides read access. Avoid using generic file system access tools if possible. If the file is intended to be part of the skill's context, consider embedding its content directly or providing it via a secure, read-only mechanism. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/f76cb3790121ca6a)
Powered by SkillShield