Security Audit

openant-ai/openant-skills:skills/send-message

github.com/openant-ai/openant-skills

AI SkillCommit 0ad720024045

TRUSTED

Scanned 25 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

openant-ai/openant-skills:skills/send-message received a trust score of 78/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned Dependency Version, Excessively Broad Bash Permissions.

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

78%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Excessively Broad Bash Permissions The declared permissions `Bash(npx @openant-ai/cli@latest status)`, `Bash(npx @openant-ai/cli@latest messages )`, and `Bash(npx @openant-ai/cli@latest notifications)` use a wildcard `` at the end. This allows the agent to execute any subcommand or argument following `status`, `messages`, or `notifications` within the `@openant-ai/cli` tool. If the CLI tool has dangerous or unintended subcommands (e.g., for file manipulation, arbitrary code execution, or destructive actions), these would be permitted, potentially leading to data loss, unauthorized actions, or privilege escalation. Restrict the `Bash` permissions to only the specific subcommands and argument patterns required by the skill. For example, instead of `Bash(npx @openant-ai/cli@latest messages )`, specify `Bash(npx @openant-ai/cli@latest messages send --userId --content )`, `Bash(npx @openant-ai/cli@latest messages read )`, `Bash(npx @openant-ai/cli@latest messages conversations)`, etc., to minimize the attack surface.	Static	Manifest:1
MEDIUM	Unpinned Dependency Version The skill uses `npx @openant-ai/cli@latest` which fetches the latest version of the `@openant-ai/cli` package. This introduces a supply chain risk, as a malicious update to the package could be automatically downloaded and executed without prior review, potentially compromising the agent's environment or data. Pin the dependency to a specific, trusted version (e.g., `npx @openant-ai/cli@1.2.3`) to ensure consistent and secure execution. Regularly review and update the pinned version.	Static	SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1902c19a2e233001.svg)](https://skillshield.io/report/1902c19a2e233001)