Security Audit
skyfire-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
skyfire-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 MCP dependency grants excessive permissions, Unpinned 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 MCP dependency grants excessive permissions The skill manifest declares a dependency on the entire `rube` MCP (`"mcp": ["rube"]`). While the skill's stated purpose is "Automate Skyfire tasks", this broad dependency grants access to all tools within the `rube` MCP, not just those explicitly related to Skyfire. If the `rube` MCP contains tools with capabilities beyond Skyfire automation (e.g., general system access, other sensitive APIs), the skill implicitly gains these broader permissions. The mention of `RUBE_REMOTE_WORKBENCH` suggests a potentially general-purpose execution environment, which could further broaden the effective permissions. Restrict the `mcp` dependency to only the specific `rube` tools or sub-toolkits required for Skyfire automation, if such granular control is available (e.g., `"mcp": ["rube/skyfire"]`). Alternatively, ensure the `rube` MCP itself is strictly scoped to Skyfire-related operations. | LLM | SKILL.md:1 | |
| LOW | Unpinned MCP dependency The skill's manifest specifies a dependency on the `rube` MCP without a version constraint (`"mcp": ["rube"]`). This means the skill will always use the latest available version of the `rube` MCP. This introduces a supply chain risk, as future updates to `rube` could introduce breaking changes, vulnerabilities, or unintended functionality without explicit review or testing by the skill developer. Pin the `rube` MCP dependency to a specific, known-good version (e.g., `"mcp": ["rube@1.2.3"]`) to ensure deterministic behavior and allow for controlled updates. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/1267f3ef42eb7786)
Powered by SkillShield