Security Audit

karmiphuc/openclaw-docs-skill:root

github.com/karmiphuc/openclaw-docs-skill

AI SkillCommit 28b380c902ff

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

karmiphuc/openclaw-docs-skill:root received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 2 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Sensitive Configuration Dump to Plaintext, Unverified Remote Context Download.

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 8, 2026 (commit 28b380c9). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

93%

Dependency Graph

100%

LLM Behavioral Safety

78%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

2 findings

Shell Execution

3 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings3

Severity	Finding	Layer	Location
HIGH	Sensitive Configuration Dump to Plaintext The update script exports the full OpenClaw configuration to a plaintext JSON file (`references/local-config.json`) within the skill directory. Since the CLI configuration likely contains API keys, tokens, or authentication credentials (as implied by `config set` commands in documentation), this operation exposes sensitive secrets to the agent's context window and any systems syncing the skill directory. Modify the script to filter out sensitive fields (e.g., using `jq 'del(.. \| .token?, .key?, .password?)'`) before saving the configuration, or remove the configuration dump entirely.	LLM	references/update-skill.sh:36
MEDIUM	Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated.	Static	references/update-skill.sh:9
MEDIUM	Unverified Remote Context Download The script downloads documentation files (`commands.md`, `docs-index.md`) from a remote URL (`docs.openclaw.ai`) using `curl` without checksum verification. This introduces a Supply Chain risk where a compromised remote server could serve malicious content (Indirect Prompt Injection) that the agent subsequently ingests as trusted context. Implement checksum verification (sha256) for downloaded resources or bundle the documentation files statically within the skill package to prevent dynamic content injection.	LLM	references/update-skill.sh:25

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/4c331d8981d71f30.svg)](https://skillshield.io/report/4c331d8981d71f30)