Skip to main content

Security Audit

personal-agent

github.com/openclaw/skills
AI SkillCommit 13146e6a3d46
30
CRITICAL
Scanned 2 months ago
0
Critical
Immediate action required
7
High
Priority fixes suggested
6
Medium
Best practices review
0
Low
Acknowledged / Tracked

Trust Assessment

personal-agent received a trust score of 30/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 14 findings: 0 critical, 7 high, 6 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Shell Injection via Unquoted API Key in Curl Header, URL Injection via Unencoded Club Name.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 0/100, indicating areas for improvement.

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
100%
Static Code Analysis
65%
Dependency Graph
100%
LLM Behavioral Safety
0%

Behavioral Risk Signals

Network Access
6 findings
Filesystem Write
2 findings
Shell Execution
10 findings
Dynamic Code
8 findings
Excessive Permissions
6 findings

Security Findings14

SeverityFindingLayerLocation

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/ae3f5fdccf9b5208.svg)](https://skillshield.io/report/ae3f5fdccf9b5208)
SkillShield Badge

Powered by SkillShield