Security Audit

openant-ai/openant-skills:skills/verify-submission

github.com/openant-ai/openant-skills

AI SkillCommit 0ad720024045

TRUSTED

Scanned 26 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

openant-ai/openant-skills:skills/verify-submission 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 Comment Arguments.

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 March 5, 2026 (commit 0ad72002). 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

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via Unsanitized Comment Arguments The skill's `allowed-tools` grant broad `Bash` execution permissions for specific `npx @openant-ai/cli@latest` commands, allowing arbitrary arguments (indicated by `*`). The skill documentation demonstrates the use of a `--comment` argument in `tasks review` and `tasks verify` commands. If the LLM or the underlying execution environment does not properly sanitize or quote user-provided input for this `--comment` argument before passing it to the shell, a malicious user could inject arbitrary shell commands. For example, a comment like `'; rm -rf /'` could lead to unintended command execution on the host system. Ensure that all user-provided arguments, especially free-form text fields like `--comment`, are strictly sanitized and properly quoted/escaped before being passed to `Bash` commands. Ideally, arguments should be passed as an array to the underlying `subprocess` call to prevent shell interpretation. The `npx` command itself or the LLM's command generation logic must be hardened to prevent shell metacharacter injection.	LLM	SKILL.md:30

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/06e205272691bfbe.svg)](https://skillshield.io/report/06e205272691bfbe)