Security Audit

icypeas-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

icypeas-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 Access via Generic MCP Dependency.

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 Access via Generic MCP Dependency The skill's manifest declares a dependency on the generic 'rube' MCP (`"mcp": ["rube"]`). While the skill's stated purpose is 'Icypeas Automation', relying on a generic MCP grants the agent access to the entire suite of tools available through Rube, not just those strictly related to Icypeas. This broad access means an agent could potentially discover and execute non-Icypeas tools if its instructions are manipulated or if it deviates from the intended workflow. The skill's instructions guide the agent to search for 'Icypeas operations', but the underlying `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL` are generic and not inherently scoped to Icypeas. Consider if the skill truly requires access to the entire Rube MCP, or if a more granular dependency could be specified (e.g., `mcp: ["rube/icypeas"]` if such a mechanism exists, or if the skill could wrap specific Icypeas tools directly rather than exposing the generic Rube interface). Alternatively, add explicit guardrails within the skill's instructions to strictly limit tool discovery and execution to only Icypeas-related tools.	LLM	SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/be5658c33a11eeb5.svg)](https://skillshield.io/report/be5658c33a11eeb5)