Security Audit

callerapi-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

callerapi-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 Excessive permissions via broad Rube MCP requirement.

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

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Excessive permissions via broad Rube MCP requirement The skill's manifest requires the entire Rube MCP (`"mcp": ["rube"]`), which is a meta-tool capable of accessing and executing a wide range of other Composio toolkits. While the skill's stated purpose is Callerapi automation, the underlying permission grants access to all tools available through Rube. The skill further demonstrates this broad capability by instructing the LLM to use generic Rube tools like `RUBE_MULTI_EXECUTE_TOOL` (line 49) and `RUBE_REMOTE_WORKBENCH` (line 70), which can execute any tool, not just Callerapi-specific ones. This creates a risk where an LLM, if prompted by an attacker, could use this skill to interact with other sensitive toolkits (e.g., file system access, other SaaS integrations) that are also connected via Rube MCP, exceeding the skill's intended scope. If the skill is truly only meant for Callerapi, the `requires` in the manifest should be more granular, if Rube MCP allows, to restrict access to only the `callerapi` toolkit. Alternatively, implement strict guardrails on the LLM's usage of `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to ensure only Callerapi-related tool slugs are executed. The skill's documentation should also explicitly declare its broad access to all Rube tools if this is the intended design.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/58ad0b80338a6d86.svg)](https://skillshield.io/report/58ad0b80338a6d86)