Security Audit
salesforce-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
salesforce-automation received a trust score of 82/100, 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 Broad Salesforce Data Access and Manipulation, 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 | |
|---|---|---|---|---|
| HIGH | Broad Salesforce Data Access and Manipulation The skill exposes highly privileged Salesforce operations, notably `SALESFORCE_RUN_SOQL_QUERY` and `SALESFORCE_CREATE_A_RECORD`. `SALESFORCE_RUN_SOQL_QUERY` allows arbitrary queries against the Salesforce database, enabling retrieval of any data accessible to the connected user. `SALESFORCE_CREATE_A_RECORD` allows creating records of any object type. If an agent using this skill is compromised or given malicious instructions, these tools could be leveraged for extensive data exfiltration, modification, or denial of service within the Salesforce instance. The documentation explicitly details the power of SOQL queries, including examples of retrieving sensitive fields like `Email`. Implement strict access controls and least privilege principles for the Salesforce user account connected via Rube MCP. Ensure the agent's prompts are carefully designed to prevent misuse of these powerful tools. Consider adding guardrails or human approval steps for highly sensitive operations or broad data queries. | LLM | SKILL.md:87 | |
| MEDIUM | Unpinned Rube MCP Dependency The skill's manifest specifies a dependency on the `rube` MCP (`"requires": {"mcp": ["rube"]}`). However, no specific version is pinned. This means that any future updates to the `rube` MCP could be automatically incorporated, potentially introducing breaking changes, new vulnerabilities, or unexpected behavior without explicit review or testing. This lack of version pinning increases the supply chain risk. If the MCP ecosystem supports version pinning for dependencies, specify a precise version for `rube` (e.g., `"rube": "1.2.3"`) or a version range to ensure stability and allow for controlled updates. Regularly review and test updates to `rube` before deployment. | LLM | SKILL.md:3 |
Scan History
Embed Code
[](https://skillshield.io/report/a37727d9eb6536bd)
Powered by SkillShield