Security Audit

deepgram-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

deepgram-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, 0 high, 1 medium, and 0 low severity. Key findings include Broad tool execution capability via RUBE_REMOTE_WORKBENCH.

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 20, 2026 (commit 27904475). 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

93%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Broad tool execution capability via RUBE_REMOTE_WORKBENCH The skill's documentation for 'deepgram-automation' includes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` in its quick reference. While the skill's stated purpose is Deepgram automation, `run_composio_tool()` is a generic Composio tool execution mechanism. If `RUBE_REMOTE_WORKBENCH` allows the execution of arbitrary Composio tools (not just Deepgram-specific ones), it grants the LLM broader permissions than necessary for its stated Deepgram automation tasks. This could lead to unintended actions if the LLM is prompted to use non-Deepgram tools, expanding the attack surface beyond the intended scope. Clarify the scope of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it can execute non-Deepgram tools, consider removing this operation from a Deepgram-specific skill's documentation or explicitly restricting its use to Deepgram tools within the skill's configuration. If it is intended to be generic, the skill's description and name should reflect this broader capability.	LLM	SKILL.md:80

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/479526ac1d962c3e.svg)](https://skillshield.io/report/479526ac1d962c3e)