Security Audit

RightNow-AI/openfang:crates/openfang-skills/bundled/github

github.com/RightNow-AI/openfang

AI SkillCommit 7bd018569501

TRUSTED

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

RightNow-AI/openfang:crates/openfang-skills/bundled/github received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via unsanitized `gh api` parameters.

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 27, 2026 (commit 7bd01856). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via unsanitized `gh api` parameters The skill instructs the agent to use `gh api` with dynamic parameters like `{owner}` and `{repo}` (e.g., `gh api repos/{owner}/{repo}/pulls`). If these parameters are derived directly from untrusted user input without proper sanitization or shell escaping, an attacker could inject arbitrary shell commands. For instance, if a malicious user provides `myrepo; rm -rf /` as the `repo` name, it could lead to the execution of `rm -rf /` on the host system. The provided skill definition does not include guidance on sanitizing or escaping these dynamic inputs. Instruct the agent to rigorously sanitize and shell-escape all user-provided inputs before incorporating them into `gh CLI` or `gh api` commands. Specifically, ensure that `{owner}` and `{repo}` are validated to be valid GitHub repository components and properly escaped for the shell execution context to prevent command injection.	LLM	SKILL.md:30

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/64a7baf21d37d5e2.svg)](https://skillshield.io/report/64a7baf21d37d5e2)