Security Audit

googlephotos-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

googlephotos-automation received a trust score of 86/100, 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 Skill enables uploading arbitrary local files to Google Photos.

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

Filesystem Write

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill enables uploading arbitrary local files to Google Photos The `GOOGLEPHOTOS_UPLOAD_MEDIA` and `GOOGLEPHOTOS_BATCH_CREATE_MEDIA_ITEMS` tools accept parameters (`file_to_upload`, `files`) described as 'Local file path to upload' or 'Local file paths to upload'. This allows the agent to read and upload any file from the local filesystem (that the agent has access to) to Google Photos. If the agent is compromised via prompt injection, an attacker could instruct it to exfiltrate sensitive local files (e.g., configuration files, credentials, user data) by uploading them to a Google Photos account. Restrict the scope of file access for upload operations. Instead of arbitrary local file paths, consider: 1. Requiring the user to explicitly provide file content (e.g., base64 encoded) rather than a path. 2. Implementing a whitelist or sandbox for allowed file paths/directories. 3. If local file paths are necessary, ensure the underlying execution environment (Rube MCP, agent runtime) strictly limits the agent's filesystem access to only explicitly designated directories for media uploads, preventing access to sensitive system files. 4. Clearly document the security implications of providing local file paths to the agent.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d76fa93d12ef9c33.svg)](https://skillshield.io/report/d76fa93d12ef9c33)