Security Audit

gender-api-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

gender-api-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 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Broad Tool 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

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad Tool Access via Rube MCP The skill's manifest declares a dependency on the 'rube' Multi-Capability Platform (MCP). The skill then instructs the LLM on how to use generic Rube tools such as `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL`. While the skill's stated purpose is 'Gender API Automation' and examples often reference 'Gender API operations', the tool calls themselves (e.g., `queries: [{use_case: "your specific Gender API task"}]` for `RUBE_SEARCH_TOOLS`) do not explicitly restrict the LLM to only search for or execute tools belonging to the `gender_api` toolkit. This broad access means an attacker could craft a prompt to the LLM to discover and execute tools from other potentially sensitive toolkits available via the Rube MCP (e.g., filesystem, email, internal APIs), leading to unauthorized operations or data exfiltration beyond the intended scope of the skill. To mitigate this, the skill's instructions for `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL` should be updated to explicitly constrain their scope to the `gender_api` toolkit. This could involve adding a `toolkit` parameter to the tool calls if supported by Rube MCP, or providing explicit instructions to the LLM to filter results by toolkit. For example, modify `RUBE_SEARCH_TOOLS` calls to include `toolkit: "gender_api"` in the query parameters.	LLM	SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/7eabefed297241bf.svg)](https://skillshield.io/report/7eabefed297241bf)