Security Audit
botpress-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
botpress-automation received a trust score of 80/100, 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 Broad tool access granted via Rube MCP, Unpinned dependency on Rube MCP.
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 17, 2026 (commit 99e2a295). 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 | Broad tool access granted via Rube MCP The skill grants access to Rube MCP tools such as `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. These tools allow the LLM to discover and execute a wide range of operations on Botpress and potentially other systems connected via Rube. `RUBE_MULTI_EXECUTE_TOOL` can execute any tool discovered, and `RUBE_REMOTE_WORKBENCH` implies capabilities for complex or bulk operations, potentially including arbitrary code execution within the Rube environment. This broad access, while central to the skill's purpose, presents a significant risk if the LLM is prompted maliciously, as it could lead to unauthorized actions or data manipulation on connected systems. Implement stricter access controls or fine-grained permissions for the Rube tools exposed to the LLM. If possible, restrict the scope of `RUBE_MULTI_EXECUTE_TOOL` to a predefined set of safe operations or specific Botpress functionalities. Carefully review the capabilities of `RUBE_REMOTE_WORKBENCH` and consider if its full power is necessary for the skill's intended use. | LLM | SKILL.md:50 | |
| MEDIUM | Unpinned dependency on Rube MCP The skill's manifest specifies a dependency on the 'rube' MCP (`"mcp": ["rube"]`) without a version constraint. This means the skill will always use the latest version of the Rube MCP. If a future version of Rube MCP introduces breaking changes, vulnerabilities, or malicious functionality, this skill would automatically inherit those risks without explicit review or update by the skill developer. Pin the Rube MCP dependency to a specific, known-good version (e.g., `"mcp": ["rube@1.2.3"]`) to ensure stability and prevent unexpected behavior or security risks from future updates. Regularly review and manually update the pinned version after verifying its integrity. | LLM | manifest.json |
Scan History
Embed Code
[](https://skillshield.io/report/d22cf1bf6fe8c127)
Powered by SkillShield