Security Audit

teltel-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

teltel-automation received a trust score of 78/100, 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, Broad tool execution capabilities via Rube MCP.

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

Manifest Analysis

100%

Static Code Analysis

78%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad tool execution capabilities via Rube MCP The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which are described as general-purpose mechanisms for executing tools and running operations. `RUBE_MULTI_EXECUTE_TOOL` can execute any tool discovered via `RUBE_SEARCH_TOOLS`, and `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` suggests a powerful, potentially unconstrained execution environment. This grants the LLM broad permissions to interact with external services and perform arbitrary operations through the Rube MCP, potentially beyond the intended scope of 'Teltel automation.' An attacker could craft prompts to exploit these broad capabilities to access or manipulate other services connected to the Rube MCP, or perform unintended actions. Implement stricter access controls or scope limitations within the Rube MCP configuration for this skill, if possible. Ensure that the LLM's access is limited only to the specific Teltel tools and operations required, and that `RUBE_REMOTE_WORKBENCH` is either not exposed or is heavily sandboxed. Provide clear guidelines to the LLM on the exact tools and parameters it is allowed to use, and consider using a tool-use framework that enforces these constraints.	Static	SKILL.md:50
MEDIUM	Unpinned Rube MCP dependency The skill's manifest specifies a dependency on the 'rube' MCP without a specific version. This can lead to supply chain vulnerabilities if new versions of 'rube' introduce breaking changes, security flaws, or malicious code without the skill developer's explicit review. Unpinned dependencies make the skill susceptible to unexpected behavior or security compromises if the upstream dependency changes. Pin the 'rube' MCP dependency to a specific, known-good version (e.g., `{"mcp": ["rube@1.2.3"]}`) to ensure consistent and secure behavior. Regularly review and update pinned dependencies.	Static	SKILL.md:4

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/7a035ca5f18c1855.svg)](https://skillshield.io/report/7a035ca5f18c1855)