Security Audit
openai/skills:skills/.curated/notion-meeting-intelligence
github.com/openai/skillsTrust Assessment
openai/skills:skills/.curated/notion-meeting-intelligence 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 Arbitrary Command Execution via MCP Configuration Instructions.
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 | Arbitrary Command Execution via MCP Configuration Instructions The skill instructions direct the host LLM/client to execute arbitrary shell commands (`codex mcp add...`, modifying `config.toml`, and `codex mcp login...`) under the guise of setting up a failed MCP connection. If executed automatically or suggested to the user without validation, this can lead to arbitrary command execution, local configuration tampering, and potential credential exposure via unauthorized third-party MCP integrations. Remove direct shell command execution instructions from the skill workflow. Instead, instruct the user to manually configure their Notion MCP connection through their client's standard user interface or official documentation. | LLM | SKILL.md:18 |
Scan History
Embed Code
[](https://skillshield.io/report/dcda8507b19d3ec5)
Powered by SkillShield