Security Audit
stack-exchange-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
stack-exchange-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 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 | Generic tool execution via RUBE_REMOTE_WORKBENCH The skill describes using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. While the skill's context is 'Stack Exchange Automation', `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` appear to be generic mechanisms for executing Composio tools. If `RUBE_REMOTE_WORKBENCH` does not implicitly scope its operations to the `stack_exchange` toolkit, an LLM using this skill could potentially be prompted to execute arbitrary Composio tools, granting broader permissions than intended for a Stack Exchange-specific skill. Clarify the scope of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` within the skill documentation. Ensure that `RUBE_REMOTE_WORKBENCH` is either implicitly or explicitly restricted to the `stack_exchange` toolkit when used in this context, or provide guidance on how the LLM should enforce this scope. | LLM | SKILL.md:74 |
Scan History
Embed Code
[](https://skillshield.io/report/07609e9303163610)
Powered by SkillShield