Security Audit

doppler-secretops-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

doppler-secretops-automation received a trust score of 85/100, 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 Excessive Permissions via General Tool Execution.

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

85%

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 Findings1

Severity	Finding	Layer	Location
HIGH	Excessive Permissions via General Tool Execution The skill's stated purpose is 'Doppler Secretops automation', yet it leverages general Rube MCP execution tools like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. These tools, as described, allow the execution of 'any tool slug from search results' and provide a 'remote workbench' for `run_composio_tool()`. This grants the skill access to potentially all tools exposed by the Rube MCP, far exceeding the scope implied by 'Doppler Secretops automation'. If the Rube MCP exposes tools for other sensitive operations (e.g., file system access, network operations, other credential management), this skill could be used to perform actions beyond its intended scope, leading to privilege escalation or unintended actions. Restrict the skill's access to only the specific Rube MCP tools required for Doppler Secretops operations. This could involve: 1) Modifying the Rube MCP integration to enforce tool-level permissions based on the skill's manifest. 2) If the Rube MCP allows, explicitly listing the allowed tool slugs within the skill's configuration or documentation, and ensuring the LLM is instructed to only use those. 3) If `RUBE_REMOTE_WORKBENCH` is not strictly necessary for Doppler Secretops, remove its usage instructions or clarify its limited scope.	Static	SKILL.md:56

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/89e63dfa4716458a.svg)](https://skillshield.io/report/89e63dfa4716458a)