Security Audit
starton-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
starton-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 broad 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 broad tool execution via `RUBE_REMOTE_WORKBENCH` The skill's documentation describes the use of `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. This tool appears to allow the execution of arbitrary Composio tools, potentially extending beyond the explicit 'Starton automation' scope of this skill. If the agent has access to other Composio toolkits, this could grant overly broad execution capabilities, enabling actions not directly related to Starton. Consider if `RUBE_REMOTE_WORKBENCH` is strictly necessary for the skill's stated purpose of 'Starton automation'. If not, remove its documentation to avoid encouraging its use. If it is necessary, ensure that the Rube MCP environment is configured with appropriate access controls to limit the scope of `run_composio_tool()` to only the intended toolkits or actions. | LLM | SKILL.md:73 |
Scan History
Embed Code
[](https://skillshield.io/report/d10d11e8177583d7)
Powered by SkillShield