Security Audit

serpapi-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

serpapi-automation received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill promotes use of powerful 'workbench' tool with unclear 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

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill promotes use of powerful 'workbench' tool with unclear scope The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' and the function `run_composio_tool()` typically imply a broad execution environment that could allow arbitrary code execution, filesystem access, or network operations. If the underlying `RUBE_REMOTE_WORKBENCH` tool is not strictly sandboxed or limited to specific, safe Serpapi operations, this instruction could lead to command injection, data exfiltration, or other unauthorized actions by an attacker manipulating the LLM's input to execute malicious code via this tool. The skill does not provide any explicit warnings or constraints on the types of operations allowed by `run_composio_tool()`, making it an excessive permission risk. Clarify the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary code, implement strict sandboxing and input validation. If it's intended only for specific, safe operations, explicitly state those limitations in the skill's documentation. Consider if such a powerful tool should be exposed directly to an LLM without more robust guardrails.	LLM	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/ef380ebcbe340592.svg)](https://skillshield.io/report/ef380ebcbe340592)