Security Audit
docupilot-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
docupilot-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, 0 high, 1 medium, and 0 low severity. Key findings include Skill exposes generic tool execution via RUBE_REMOTE_WORKBENCH.
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 | |
|---|---|---|---|---|
| MEDIUM | Skill exposes generic tool execution via RUBE_REMOTE_WORKBENCH The 'docupilot-automation' skill, intended for Docupilot tasks, lists `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` in its quick reference. The name `run_composio_tool()` suggests a generic capability to execute any Composio tool, not necessarily restricted to Docupilot. If the underlying Rube MCP system allows this function to access tools from other Composio toolkits, this could grant the skill excessive permissions beyond its stated purpose, potentially enabling actions unrelated to Docupilot. Clarify the scope of `run_composio_tool()` within this skill. If it is indeed restricted to Docupilot operations, update the documentation to reflect this. If it can execute arbitrary Composio tools, consider if this broad capability is necessary for a Docupilot-specific skill, and if not, replace it with a more narrowly scoped tool or remove it. | LLM | SKILL.md:69 |
Scan History
Embed Code
[](https://skillshield.io/report/e2f3693e0e6b05c2)
Powered by SkillShield