Security Audit

smartrecruiters-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

smartrecruiters-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 Broad Tool Execution via RUBE_REMOTE_WORKBENCH, Unverified External MCP and Toolkits.

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

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution via RUBE_REMOTE_WORKBENCH The skill utilizes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. While the skill's stated purpose is Smartrecruiters automation, the `run_composio_tool()` primitive is generically named. If the underlying Rube MCP allows this function to execute arbitrary Composio tools or code beyond the intended Smartrecruiters toolkit, it could lead to excessive permissions and potential for privilege escalation or unintended actions. The documentation does not explicitly state that `run_composio_tool()` is strictly confined to the `smartrecruiters` toolkit for this skill. Clarify and enforce strict scope limitations for `run_composio_tool()` within the Rube MCP, ensuring it can only interact with the `smartrecruiters` toolkit for this skill. Document these limitations clearly in the skill's description.	Static	SKILL.md:70
MEDIUM	Unverified External MCP and Toolkits The skill relies entirely on the Rube MCP (`https://rube.app/mcp`) and Composio toolkits (`https://composio.dev`). There is no explicit version pinning or integrity verification mechanism described for these external dependencies. A compromise or malicious update to the Rube MCP or Composio toolkits could introduce vulnerabilities into this skill without any changes to the skill's local files, posing a supply chain risk. Implement mechanisms for version pinning or integrity checking of the Rube MCP and Composio toolkits. Consider using a trusted registry or local caching with checksum verification to ensure the integrity of external dependencies.	Static	SKILL.md:20

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/924b898a3f5bd6df.svg)](https://skillshield.io/report/924b898a3f5bd6df)