Security Audit
bolt-iot-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
bolt-iot-automation received a trust score of 83/100, 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 Unpinned MCP dependency, Potentially excessive permissions via generic execution primitive.
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 | Potentially excessive permissions via generic execution primitive The skill documentation highlights `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' using `run_composio_tool()`. This description suggests a highly generic and powerful execution primitive. If `run_composio_tool()` is not adequately sandboxed, restricted, or validated, an LLM could be prompted to perform arbitrary or highly privileged actions, leading to excessive permissions being exploited for unintended 'bulk operations' or even command injection. The broad scope implied by 'Bulk ops' and a generic `run_composio_tool()` without further context on its limitations poses a significant risk. Provide clear documentation and examples of safe, restricted usage for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Implement strict input validation, access controls, and sandboxing for `run_composio_tool()` to prevent arbitrary code execution or unintended privileged actions. Consider if such a generic 'bulk ops' tool is necessary or if more specific, limited tools could be used instead. | LLM | SKILL.md:70 | |
| MEDIUM | Unpinned MCP dependency The skill manifest specifies a dependency on the 'rube' MCP without a version constraint. This means the skill could inadvertently use a future version of Rube MCP that contains vulnerabilities or malicious code, leading to supply chain risks. Without version pinning, there's no guarantee of consistent and secure behavior across different deployments or over time. Pin the Rube MCP dependency to a specific, known-good version or version range (e.g., `{"mcp": ["rube==1.2.3"]}` or `{"mcp": ["rube>=1.0.0,<2.0.0"]}`) to ensure stability and mitigate supply chain risks. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/3ae8da178ea3c85f)
Powered by SkillShield