Security Audit
axonaut-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
axonaut-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 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned MCP Dependency and External Service Reliance, Broad Tool Access via 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 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 | |
|---|---|---|---|---|
| MEDIUM | Unpinned MCP Dependency and External Service Reliance The skill's manifest declares a dependency on the 'rube' MCP without specifying a version or hash, and the skill's instructions rely on external services hosted at `rube.app` and `composio.dev`. This introduces a supply chain risk, as changes or compromises to these unpinned external components could impact the skill's security and functionality without explicit updates or checks. If possible, specify a version or hash for the 'rube' MCP dependency. Implement robust validation and monitoring of external services (`rube.app`, `composio.dev`) to detect unauthorized changes or compromises. | LLM | SKILL.md:1 | |
| MEDIUM | Broad Tool Access via Rube MCP The skill instructs the agent to utilize powerful Rube MCP tools such as `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` (which includes `run_composio_tool()`). These tools grant extensive capabilities to perform various operations within Axonaut. If the agent's instructions are compromised or untrusted inputs are processed, these powerful tools could be misused to perform unauthorized actions on the Axonaut platform, leading to excessive permissions being leveraged. Implement strict input validation and authorization checks for all arguments passed to `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. Ensure the agent operates with the principle of least privilege and that user consent is obtained for sensitive operations before executing these powerful tools. | LLM | SKILL.md:60 |
Scan History
Embed Code
[](https://skillshield.io/report/abdc725ceb7ef098)
Powered by SkillShield