Security Audit
bouncer-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
bouncer-automation received a trust score of 93/100, 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 access to external system operations via Rube MCP tools, 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 access to external system operations via Rube MCP tools The skill utilizes `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which, after discovering available tools via `RUBE_SEARCH_TOOLS`, can execute any operation exposed by the Bouncer toolkit through the Rube MCP. This grants the LLM broad capabilities within the Bouncer system, including potentially sensitive actions depending on the Bouncer toolkit's full scope. While necessary for the skill's stated purpose ('Automate Bouncer tasks'), this broad access could be misused if the LLM is compromised or given incorrect instructions, leading to unauthorized data manipulation, deletion, or access within Bouncer. Implement strict access controls and monitoring on the Bouncer toolkit itself to limit the scope of operations available to the Rube MCP. Ensure the LLM's operational context is sandboxed and its instructions are carefully validated to prevent unintended or malicious use of these broad capabilities. Consider implementing fine-grained permissions for specific Bouncer operations if possible. | LLM | SKILL.md:48 | |
| LOW | Unpinned Rube MCP dependency The skill's manifest declares a dependency on the 'rube' MCP (`"mcp": ["rube"]`) without specifying a version. This means the skill will always interact with the latest version of the Rube MCP. If the Rube MCP introduces breaking changes or, in a worst-case scenario, malicious functionality, the skill would automatically incorporate it without explicit review or version control, potentially leading to unexpected behavior or security vulnerabilities. If the Rube MCP supports versioning for its API or tools, specify a minimum or exact version in the `requires` section of the manifest to ensure stability and security. If versioning is not supported, ensure robust monitoring of the Rube MCP for changes and potential security advisories. | LLM | Manifest (frontmatter JSON):1 |
Scan History
Embed Code
[](https://skillshield.io/report/9bdb76e935bc736b)
Powered by SkillShield