Security Audit

grist-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

grist-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 Agent granted broad, dynamic tool execution capabilities.

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

85%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Agent granted broad, dynamic tool execution capabilities The skill instructs the agent to dynamically discover and execute any available tool from the 'grist' toolkit via `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH`. This design grants the agent the sum of all permissions offered by the underlying 'grist' toolkit. If the 'grist' toolkit includes highly privileged or destructive operations (e.g., data deletion, access control modification, sensitive data access), the agent will have the capability to perform these actions without explicit constraints defined within this skill's documentation. The `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` further implies a generic remote execution capability, which could be leveraged for unintended operations. Implement granular access controls or explicit whitelisting/blacklisting of specific Grist operations within the Rube MCP or Composio configuration. If not possible at the platform level, the skill's prompt should explicitly instruct the LLM to only use a predefined, limited set of safe Grist operations, or require human confirmation for sensitive actions before executing tools.	LLM	SKILL.md:30

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/6703b3333b6668c8.svg)](https://skillshield.io/report/6703b3333b6668c8)