Trust Assessment
dpd2-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 Skill recommends use of RUBE_REMOTE_WORKBENCH which may allow arbitrary code execution.
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 | Skill recommends use of RUBE_REMOTE_WORKBENCH which may allow arbitrary code execution The skill documentation explicitly recommends using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. A 'remote workbench' typically implies an environment capable of executing arbitrary code or complex operations. If `run_composio_tool()` can be supplied with user-controlled arguments or code, this could lead to command injection, allowing an attacker to execute arbitrary commands on the host system or within the workbench environment. This also presents a significant data exfiltration risk (SS-LLM-002) if the executed code can access sensitive files or network resources. The broad nature of 'bulk ops' and 'workbench' suggests potentially excessive permissions (SS-LLM-005) for operations initiated through this tool. Clarify the exact capabilities and security boundaries of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary code execution, restrict its use or provide strong input validation and sandboxing. If it's intended for specific, safe operations, document those limitations clearly. Consider if this tool is truly necessary for the skill's intended purpose or if a more constrained alternative exists. | LLM | SKILL.md:68 |
Scan History
Embed Code
[](https://skillshield.io/report/6a490ceb0c60ab0a)
Powered by SkillShield