Trust Assessment
cal-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 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Ambiguous RUBE_REMOTE_WORKBENCH capability.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Ambiguous RUBE_REMOTE_WORKBENCH capability The skill describes using `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. The documentation provided within the skill does not specify the exact capabilities or security boundaries of this tool. If `run_composio_tool()` allows arbitrary code execution, shell commands, or highly privileged operations beyond standard API calls, it could lead to command injection or excessive permissions, allowing an attacker to execute malicious code or perform unauthorized actions on the host system or connected services. The term 'workbench' often implies a flexible and potentially broad execution environment. Clarify the precise capabilities and security boundaries of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary code execution, implement strict sandboxing, input validation, and least privilege principles. If it's intended for bulk execution of specific Composio tools, ensure that the scope of operations is clearly defined and limited, and that proper authorization checks are in place for each bulk operation. The skill's description should explicitly state these limitations. | LLM | SKILL.md:68 |
Scan History
Embed Code
[](https://skillshield.io/report/ed5c9242ee6a2a77)
Powered by SkillShield