Security Audit
google-cloud-vision-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
google-cloud-vision-automation 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 Excessive Permissions via Broad Tool 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 27904475). 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 | Excessive Permissions via Broad Tool Access The skill instructs the LLM to discover and execute any available Google Cloud Vision operation via `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL`. This design grants the LLM access to the full scope of permissions configured for the underlying Google Cloud Vision connection within Rube MCP. If this connection is configured with overly broad permissions (e.g., full 'cloud-platform' access or similar broad scopes), the LLM could be leveraged to perform actions beyond the user's explicit intent, potentially leading to unauthorized data access, modification, or deletion. The skill itself does not enforce granular permission control, relying entirely on the external Rube MCP connection's configuration. Ensure that the Google Cloud Vision connection configured in Rube MCP adheres strictly to the principle of least privilege. Grant only the minimum necessary permissions required for the intended Google Cloud Vision operations. Regularly review and audit the scopes and roles assigned to the Google Cloud Vision service account or user used for the connection. | LLM | SKILL.md:48 |
Scan History
Embed Code
[](https://skillshield.io/report/fe7914ed6b0bf02d)
Powered by SkillShield