Security Audit

agentic-ai-gold

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

agentic-ai-gold received a trust score of 87/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Unpinned Python Dependencies in Installation Script.

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 12, 2026 (commit 13146e6a). 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

93%

Behavioral Risk Signals

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
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	skills/amitabhainarunachala/agentic-ai-gold/install.sh:29
MEDIUM	Unpinned Python Dependencies in Installation Script The `install.sh` script installs several Python packages (`langgraph`, `openai-agents`, `crewai`, `pydantic-ai`, `mem0`, `zep-python`) without specifying exact version numbers. This practice, known as unpinned dependencies, introduces a supply chain risk. If a future version of any of these packages contains a vulnerability or malicious code, the installation process will automatically pull in the compromised version, potentially leading to security breaches or unexpected behavior. While this is an installation script and not part of the agent's runtime, it directly impacts the security posture of the deployed skill. Pin all Python dependencies to specific, known-good versions (e.g., `package==1.2.3`). Alternatively, use a `requirements.txt` file with pinned versions and install using `pip install -r requirements.txt`. Regularly audit and update these pinned versions to benefit from security patches while maintaining control over dependency versions.	LLM	install.sh:19

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/0b112a1032e4b4e4.svg)](https://skillshield.io/report/0b112a1032e4b4e4)