skills/jeremylongshore/tons-of-skills-marketplace/notion-advanced-troubleshooting/Gen Agent Trust Hub
notion-advanced-troubleshooting
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with the external Notion API to retrieve page, database, and block content, creating a surface for indirect prompt injection.
- Ingestion points: Data is fetched from external sources using
notion.pages.retrieve,notion.databases.query, andnotion.blocks.children.listinreferences/implementation.md. - Boundary markers: The instructions do not define specific delimiters or "ignore" instructions to prevent the agent from accidentally following commands embedded within Notion content.
- Capability inventory: The skill utilizes
Bash(curl:*)andBash(node:*)as specified in theallowed-toolsconfiguration inSKILL.md. - Sanitization: While the skill validates metadata and property types, it does not sanitize or filter the natural language content retrieved from Notion blocks.
Audit Metadata