Security Audit

openclaw-nextcloud

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

openclaw-nextcloud received a trust score of 71/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Unsafe deserialization / dynamic eval, Excessive 'Bash Read' Permission Declared.

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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

85%

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 Findings2

Severity	Finding	Layer	Location
HIGH	Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions.	Manifest	skills/keithvassallomt/openclaw-nextcloud/scripts/nextcloud.js:14382
HIGH	Excessive 'Bash Read' Permission Declared The skill declares 'Bash Read' permission in its manifest, which grants it the ability to read arbitrary files on the host system. The described functionality of the skill (managing Nextcloud resources via CalDAV, WebDAV, and Notes API) primarily involves network communication with a remote Nextcloud instance. Local file system read access is not justified by the skill's stated purpose, posing an unnecessary security risk if the skill or the agent using it is compromised or misused. Review and restrict the 'allowed-tools' permission to only those strictly necessary for the skill's operation. If the skill only interacts with a remote Nextcloud instance, 'Bash Read' should be removed. If local file access is genuinely required (e.g., for temporary storage or configuration), specify more granular permissions or restrict paths.	LLM	skills/keithvassallomt/openclaw-nextcloud/SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/768f5a3fb7d975d8.svg)](https://skillshield.io/report/768f5a3fb7d975d8)