Security Audit

callerapi-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 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 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 Potential for Excessive Tool Permissions via Rube MCP, Unpinned Dependency on Rube MCP.

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

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Potential for Excessive Tool Permissions via Rube MCP The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` for 'Callerapi operations' and `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. While the exact scope of these operations is not detailed within the skill's documentation, the names 'multi-execute tool' and 'remote workbench' (especially with 'run_composio_tool()') suggest potentially broad and unconstrained execution capabilities. If the underlying Rube MCP tools grant extensive access to external APIs, file systems, or arbitrary code execution, this skill effectively provides the LLM with excessive permissions, increasing the attack surface for malicious use or unintended actions. The dynamic discovery of tools via `RUBE_SEARCH_TOOLS` further amplifies this risk by allowing the LLM to potentially access a wide range of functionalities not explicitly listed. Clarify and restrict the scope of operations allowed by `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. Implement granular permissions within Rube MCP to ensure the LLM can only perform necessary actions. If `RUBE_REMOTE_WORKBENCH` allows arbitrary code execution, ensure it is heavily sandboxed and its use is strictly controlled.	Static	SKILL.md:47
MEDIUM	Unpinned Dependency on Rube MCP The skill's manifest specifies a dependency on 'rube' MCP without a version constraint (`'mcp': ['rube']`). This means the skill will use whatever version of Rube MCP is currently available, which could change over time. An unpinned dependency introduces a supply chain risk, as a malicious or vulnerable update to Rube MCP could be automatically incorporated, potentially compromising the skill's security or stability. Pin the dependency on Rube MCP to a specific, known-good version (e.g., `'mcp': ['rube@1.2.3']`) to ensure consistent behavior and prevent unexpected changes from upstream dependencies. Regularly review and update pinned versions.	Static	Manifest:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/61b04228cdbb59d4.svg)](https://skillshield.io/report/61b04228cdbb59d4)