Security Audit
leadfeeder-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
leadfeeder-automation received a trust score of 92/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Broad tool access via Rube MCP, Unpinned Rube MCP dependency.
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 | |
|---|---|---|---|---|
| MEDIUM | Broad tool access via Rube MCP The skill's manifest requires access to the `rube` MCP, which is a general-purpose tool orchestration engine. While the skill's intended use is Leadfeeder automation, granting an agent access to this skill effectively grants access to the entire `rube` MCP interface, including powerful primitives like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. This allows the agent to potentially interact with any toolkit connected to Rube (not just Leadfeeder) if the agent is compromised or misdirected, leading to broader access than strictly necessary for Leadfeeder tasks. Evaluate if the skill truly requires full `rube` MCP access, or if a more granular permission model is available within the Composio ecosystem. Ensure the agent's instructions are strictly scoped to Leadfeeder operations and that the agent's environment is secured against compromise. | LLM | SKILL.md:1 | |
| LOW | Unpinned Rube MCP dependency The skill's manifest specifies a dependency on the `rube` MCP (`"mcp": ["rube"]`) without a version constraint. This means the skill will always use the latest available version of `rube`. This can lead to unexpected behavior, breaking changes, or the introduction of vulnerabilities if future `rube` versions are incompatible or compromised, without explicit action from the skill developer. Pin the `rube` MCP dependency to a specific, tested version to ensure stability and security. Regularly review and update the pinned version to benefit from security patches and new features. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/94ad52373bebba0e)
Powered by SkillShield