Security Audit
openai/skills:skills/.curated/notion-research-documentation
github.com/openai/skillsTrust Assessment
openai/skills:skills/.curated/notion-research-documentation 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 Remote MCP Client and Arbitrary Command Execution Risk.
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 July 17, 2026 (commit 49f948fa). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Remote MCP Client and Arbitrary Command Execution Risk The skill instructions direct the LLM/agent to execute local shell commands (`codex mcp add`, `codex --enable rmcp_client`, and modifying `config.toml`) to enable a remote MCP client (`rmcp_client = true`). Enabling remote MCP clients without explicit user consent can allow external servers to execute arbitrary tools or commands on the user's local machine, posing a severe security risk. Do not instruct the LLM to automatically run configuration commands that enable remote MCP clients or modify local configuration files. Instead, instruct the user to perform these setup steps manually in their terminal. | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/30d50e9b468fd272)
Powered by SkillShield