Security Audit

bigmailer-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

bigmailer-automation received a trust score of 86/100, 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, 0 high, 2 medium, and 0 low severity. Key findings include Generic Tool Execution via Rube MCP, Generic Workbench Access 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

86%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Shell Execution

2 findings

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
MEDIUM	Generic Tool Execution via Rube MCP The skill exposes generic Rube MCP tools (`RUBE_MULTI_EXECUTE_TOOL`) which allow the execution of arbitrary tools discovered via `RUBE_SEARCH_TOOLS`. While the skill's stated purpose is 'Bigmailer automation', these generic execution capabilities could potentially be leveraged by a malicious prompt to execute operations beyond Bigmailer, depending on what tools Rube MCP makes available and what other connections are active. The skill itself does not enforce a strict whitelist of allowed Bigmailer operations, relying instead on the LLM's adherence to the prompt and Rube's discovery mechanism. This broad access increases the risk of unintended actions if the LLM is compromised or misdirected. If possible, restrict the Rube MCP tools exposed by the skill to a specific whitelist of Bigmailer-related operations. Alternatively, ensure that the Rube MCP itself has robust access control and auditing to prevent unauthorized execution of tools outside the intended scope. Implement strong guardrails in the LLM to prevent it from calling generic execution tools for unintended purposes.	Static	SKILL.md:60
MEDIUM	Generic Workbench Access via Rube MCP The skill explicitly mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This suggests access to a more general execution environment within Rube MCP, which could allow for broader operations than strictly Bigmailer-related tasks. A 'workbench' typically implies a powerful, less constrained execution context. This increases the attack surface if the LLM is prompted to execute arbitrary Composio tools through this workbench, potentially leading to unauthorized actions on other connected services. Review the capabilities of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If they allow execution of arbitrary Composio tools, consider if this level of generality is necessary for Bigmailer automation. If not, restrict the skill's access to this tool or provide more specific, Bigmailer-scoped alternatives. Implement strong guardrails in the LLM to prevent misuse.	Static	SKILL.md:90

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/64dc8f31203cef93.svg)](https://skillshield.io/report/64dc8f31203cef93)