Skip to main content

Security Audit

phone-agent

github.com/openclaw/skills
AI SkillCommit 13146e6a3d46
10
CRITICAL
Scanned 2 months ago
4
Critical
Immediate action required
4
High
Priority fixes suggested
11
Medium
Best practices review
1
Low
Acknowledged / Tracked

Trust Assessment

phone-agent received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 20 findings: 4 critical, 4 high, 11 medium, and 1 low severity. Key findings include Unsafe environment variable passthrough, File read + network send exfiltration, Credential harvesting.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis 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
0%
Static Code Analysis
85%
Dependency Graph
30%
LLM Behavioral Safety
76%

Behavioral Risk Signals

Network Access
4 findings
Filesystem Write
4 findings
Shell Execution
1 finding
Dynamic Code
1 finding
Excessive Permissions
5 findings

Security Findings20

SeverityFindingLayerLocation

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1ed2dfcc8a022e15.svg)](https://skillshield.io/report/1ed2dfcc8a022e15)
SkillShield Badge

Powered by SkillShield