Security Audit
claid-ai-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
claid-ai-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 Potential for Command Injection/Excessive Permissions via RUBE_REMOTE_WORKBENCH, Unpinned 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 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 | Potential for Command Injection/Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill documentation references `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. Tools like 'workbench' or those allowing arbitrary 'run' commands often provide broad execution capabilities. If `run_composio_tool()` permits arbitrary code execution or shell commands, it could be exploited for command injection, data exfiltration, or other malicious activities by an attacker crafting specific inputs to the agent. The skill promotes the use of this powerful tool without detailing its security boundaries. Review the implementation of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` within the Rube MCP to ensure it is properly sandboxed and does not allow arbitrary code execution. If it does, consider restricting its capabilities or providing clear warnings and usage guidelines. If not strictly necessary, remove or limit access to such a powerful tool. | LLM | SKILL.md:80 | |
| MEDIUM | Unpinned Dependency in Manifest The skill's manifest declares a dependency on the 'rube' Multi-Capability Provider (MCP) without specifying a version. This 'unpinned' dependency means that the latest version of 'rube' will always be used. If a future version of 'rube' introduces vulnerabilities, breaking changes, or malicious code (e.g., through a supply chain attack on the 'rube' project), this skill could automatically inherit those risks without explicit review or approval, potentially leading to compromise. Pin the version of the 'rube' MCP in the `requires` section of the manifest (e.g., `"rube": "^1.0.0"` or `"rube": "1.2.3"`). This ensures that updates are explicitly reviewed and approved before being incorporated, mitigating the risk of unexpected changes or supply chain attacks. | LLM | Manifest (frontmatter JSON):1 |
Scan History
Embed Code
[](https://skillshield.io/report/b033c0b12682bc88)
Powered by SkillShield