Security Audit

endorsal-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

endorsal-automation received a trust score of 88/100, 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 Use of RUBE_REMOTE_WORKBENCH grants broad operational scope.

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

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Use of RUBE_REMOTE_WORKBENCH grants broad operational scope The skill documentation suggests using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This implies a powerful interface that could allow the LLM to perform complex, potentially unconstrained, or high-volume operations on the Endorsal system. Granting an autonomous agent access to such a 'workbench' tool can lead to excessive permissions, allowing it to execute actions beyond the intended scope or with greater impact than individual, granular tool calls. The exact capabilities and security implications of `run_composio_tool()` are not detailed, but the term 'workbench' suggests a flexible and potentially programmable environment, which poses a significant risk when exposed to an LLM. Restrict the LLM's access to `RUBE_REMOTE_WORKBENCH` or ensure that `run_composio_tool()` is strictly sandboxed and only allows pre-approved, granular operations. Provide clear documentation on the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` to allow for proper risk assessment and control. If possible, prefer more granular tools over a 'workbench' for agent interactions to enforce the principle of least privilege.	LLM	SKILL.md:75

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e934a1a5dc11e32c.svg)](https://skillshield.io/report/e934a1a5dc11e32c)