Security Audit
finage-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
finage-automation received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned Rube MCP dependency, Instruction to use potentially overly broad `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 17, 2026 (commit 99e2a295). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned Rube MCP dependency The skill's manifest specifies a dependency on the 'rube' MCP without a version constraint. This allows the agent to use any version of the 'rube' MCP, including potentially outdated or compromised versions, introducing a significant supply chain risk. An attacker could potentially introduce a malicious version of the 'rube' MCP that the agent might unknowingly use. Pin the 'rube' MCP dependency to a specific, known-good version or version range in the manifest to ensure stability and security. For example, `"mcp": ["rube@^1.0.0"]`. | LLM | Manifest | |
| MEDIUM | Instruction to use potentially overly broad `RUBE_REMOTE_WORKBENCH` The skill instructs the agent to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' and 'remote' often imply broad capabilities, and without explicit limitations or sandboxing described for `run_composio_tool()`, this function could potentially allow arbitrary code execution or broad access to system resources. This could lead to excessive permissions for the agent if the underlying `rube` MCP or `composio_tool` is not properly secured or sandboxed. Clarify the scope and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` within the skill documentation. If it allows arbitrary execution, consider if this level of access is truly necessary and implement strict sandboxing or permission controls within the `rube` MCP to mitigate potential abuse. | LLM | SKILL.md:80 |
Scan History
Embed Code
[](https://skillshield.io/report/4e9113a52d3cfe9b)
Powered by SkillShield