Security Audit

salesforce-service-cloud-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

salesforce-service-cloud-automation received a trust score of 85/100, 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 Potential Prompt Injection via Natural Language Query, Unspecified Execution Capabilities via 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 20, 2026 (commit 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

78%

Behavioral Risk Signals

Shell Execution

2 findings

Dynamic Code

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unspecified Execution Capabilities via RUBE_REMOTE_WORKBENCH The `RUBE_REMOTE_WORKBENCH` tool is listed for 'Bulk ops' with the approach `run_composio_tool()`. The term 'workbench' often implies a powerful, potentially unconstrained execution environment, and `run_composio_tool()` suggests the ability to execute arbitrary code or complex operations. Without clear documentation on the security model and limitations of `run_composio_tool()`, this presents a significant risk of command injection or excessive permissions. An attacker could potentially leverage this tool to execute unauthorized commands, access sensitive data, or perform broad operations within the Rube environment or connected Salesforce instance. Provide detailed documentation on the exact capabilities, security implications, and input validation for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary code execution, it should be restricted to trusted users, sandboxed, or removed. Ensure that any user-supplied arguments to this tool are strictly validated and sanitized to prevent command injection.	LLM	SKILL.md:79
MEDIUM	Potential Prompt Injection via Natural Language Query The skill's usage examples for `RUBE_SEARCH_TOOLS` demonstrate passing natural language input via the `use_case` field (e.g., `use_case: "your specific Salesforce Service Cloud task"`). If the Rube MCP system processes this `use_case` using an internal LLM, a malicious user could craft a prompt injection attack within this field. This could manipulate Rube's internal LLM to select unintended tools, alter query parameters, or perform actions beyond the user's explicit intent, leading to unauthorized operations or information disclosure. Implement robust input validation and sanitization for natural language inputs passed to `use_case` fields, especially if they are processed by an LLM. Consider using structured inputs, whitelisting allowed terms, or employing LLM-specific prompt injection defenses to prevent manipulation of downstream LLMs.	LLM	SKILL.md:46

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/dee9002a2c794fcf.svg)](https://skillshield.io/report/dee9002a2c794fcf)