Security Audit
pushbullet-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
pushbullet-automation received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential for broad tool execution via RUBE_REMOTE_WORKBENCH, Unpinned Rube MCP dependency in manifest.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential for broad tool execution via RUBE_REMOTE_WORKBENCH The skill documentation mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This suggests a powerful mechanism for executing Composio tools, potentially bypassing the explicit recommendation to `RUBE_SEARCH_TOOLS` first for schema validation. If `run_composio_tool()` can execute arbitrary tools or commands without strict input validation and sandboxing, it could lead to excessive permissions, allowing the LLM to perform actions beyond its intended scope or even execute arbitrary code. The 'workbench' nature implies a less constrained environment, increasing the risk of misuse. Clarify the exact capabilities and security boundaries of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that `run_composio_tool()` strictly validates inputs, adheres to the principle of least privilege, and operates within a secure, sandboxed environment. Provide clear guidance on how to prevent its misuse for unauthorized or unintended operations. | LLM | SKILL.md:60 | |
| MEDIUM | Unpinned Rube MCP dependency in manifest The skill's manifest specifies a dependency on `mcp: ["rube"]` without a version constraint. This means the skill will rely on whatever version of the Rube MCP is currently available. An unpinned dependency can introduce supply chain risks, as a breaking change or a malicious update to the Rube MCP could affect the skill's functionality or security without explicit user intervention or awareness. Specify a version constraint for the `rube` MCP dependency (e.g., `mcp: ["rube@^1.0.0"]`) in the manifest to ensure compatibility and prevent unexpected behavior or security issues from future updates. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/e2845a85084dd49c)
Powered by SkillShield