Security Audit
seo-cannibalization-detector
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
seo-cannibalization-detector 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 instructs LLM to open local file, implying file system 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 instructs LLM to open local file, implying file system access The skill's instructions include 'open `resources/implementation-playbook.md`'. This indicates that the LLM is expected to have file system access to read local files. If the LLM's file access permissions are not strictly confined to the skill's intended resources, this could lead to unauthorized access to other files on the system, potentially exposing sensitive information or allowing for data exfiltration. Ensure the LLM's file system access is strictly sandboxed and limited only to necessary, non-sensitive files within the skill's directory. Avoid instructing the LLM to open files that might contain sensitive data or are outside its designated scope. If `resources/implementation-playbook.md` contains sensitive information, consider alternative methods for providing examples or ensure it's sanitized. | LLM | SKILL.md:16 |
Scan History
Embed Code
[](https://skillshield.io/report/687a98ad925789f2)
Powered by SkillShield