Security Audit
needle-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
needle-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 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 | |
|---|---|---|---|---|
| HIGH | Broad tool execution via RUBE_REMOTE_WORKBENCH The skill's 'Quick Reference' section exposes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. While the skill is named 'needle-automation' and described as automating 'Needle tasks', the `run_composio_tool()` function implies the ability to execute arbitrary Composio tools, not just Needle-specific ones. This grants permissions far beyond the stated purpose of the skill, potentially allowing access to or manipulation of other systems connected via Composio, increasing the attack surface. Clarify the scope and restrictions of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it is intended to be restricted to Needle tools, ensure this is enforced by the underlying Rube MCP and explicitly stated in the skill's documentation. If broader capabilities are intended, update the skill's name, description, and manifest to accurately reflect these extensive permissions and the associated risks. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/fea682265aaacf7f)
Powered by SkillShield