Security Audit

api-ninjas-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

api-ninjas-automation received a trust score of 78/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Skill exposes highly privileged `RUBE_REMOTE_WORKBENCH` tool, Skill enables execution of arbitrary tools via `RUBE_MULTI_EXECUTE_TOOL`.

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

78%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

2 findings

Dynamic Code

2 findings

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Skill exposes highly privileged `RUBE_REMOTE_WORKBENCH` tool The skill documentation explicitly mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This tool typically allows for arbitrary execution of Composio tools, which can include filesystem access, network requests, and other sensitive operations, potentially outside the scope of 'API Ninjas Automation'. An attacker could leverage prompt injection to instruct the agent to use this highly privileged tool for malicious purposes, leading to data exfiltration, command injection, or other compromises. Restrict the agent's access to `RUBE_REMOTE_WORKBENCH` or provide clear guidelines and guardrails within the skill's instructions to prevent its misuse. If `RUBE_REMOTE_WORKBENCH` is not strictly necessary for API Ninjas automation, consider removing its mention or providing a more constrained alternative.	Static	SKILL.md:80
MEDIUM	Skill enables execution of arbitrary tools via `RUBE_MULTI_EXECUTE_TOOL` The skill instructs the agent to use `RUBE_MULTI_EXECUTE_TOOL` with `tool_slug`s discovered from `RUBE_SEARCH_TOOLS`. While the skill's stated purpose is 'API Ninjas Automation', `RUBE_SEARCH_TOOLS` is a general tool discovery mechanism and could return tools unrelated to API Ninjas. An attacker could use prompt injection to trick the agent into discovering and executing other powerful tools available through Rube MCP, potentially leading to actions outside the intended scope of the skill. Implement stricter filtering or validation on the `tool_slug`s passed to `RUBE_MULTI_EXECUTE_TOOL` to ensure only API Ninjas-related tools are executed. Alternatively, constrain the agent's access to only specific `api_ninjas` tools.	Static	SKILL.md:55

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/dabd63ae12115d88.svg)](https://skillshield.io/report/dabd63ae12115d88)