Security Audit
zeplin-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
zeplin-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 Broad execution capabilities 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 | |
|---|---|---|---|---|
| HIGH | Broad execution capabilities via RUBE_REMOTE_WORKBENCH The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` which can execute `run_composio_tool()`. This implies the ability to perform 'Bulk ops' and potentially execute arbitrary Composio tools. If Composio tools extend beyond Zeplin-specific operations or include capabilities like filesystem access, network requests, or arbitrary code execution, this grants the LLM excessive permissions, potentially leading to privilege escalation or unintended system access. Restrict the capabilities of `RUBE_REMOTE_WORKBENCH` to only Zeplin-specific operations or provide clear documentation on its security implications. If `run_composio_tool()` can execute arbitrary code or non-Zeplin tools, this should be explicitly called out and heavily restricted, ideally by limiting the scope of tools it can invoke or by sandboxing its execution environment. | LLM | SKILL.md:80 |
Scan History
Embed Code
[](https://skillshield.io/report/0b17137962e29b96)
Powered by SkillShield