Trust Assessment
notion-api received a trust score of 86/100, 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 User Input in Curl Commands.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, static_code_analysis, dependency_graph. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 11, 2026 (commit 326f2466). 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 | Potential Command Injection via Unsanitized User Input in Curl Commands The skill provides numerous `curl` command examples that are intended to be executed by the AI agent. These examples include placeholders for dynamic values such as `{page_id}`, `{block_id}`, `search term`, and JSON payload content. If the AI agent directly substitutes user-provided input into these placeholders without proper shell escaping or JSON sanitization, a malicious user could inject shell metacharacters (e.g., `;`, `&`, `|`, `` ` ``) or malformed JSON to execute arbitrary commands on the host system where the `curl` command is run. The skill does not provide any explicit instructions or warnings about sanitizing user input before constructing and executing these shell commands. Instruct the AI agent to rigorously sanitize and escape all user-provided input before incorporating it into shell commands or JSON payloads. For shell commands, this means escaping all shell metacharacters. For JSON payloads, this means properly encoding user input as JSON strings. Ideally, the agent should use a dedicated HTTP client library in a programming language (e.g., Python's `requests` library) rather than constructing raw `curl` commands, as libraries handle much of this sanitization automatically. If shell execution is unavoidable, provide explicit guidance on using safe shell escaping functions. | Unknown | SKILL.md:50 |
Scan History
Embed Code
[](https://skillshield.io/report/37b017bcbc3bd083)
Powered by SkillShield