skills/g1joshi/agent-skills/notion/Gen Agent Trust Hub

notion

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @notionhq/client package via npm. This is the official SDK for a well-known service and is considered a safe dependency.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external sources (such as GitHub PRs and Jira tickets) into Notion databases and pages. This creates a potential surface for indirect prompt injection where malicious instructions embedded in external tickets could influence agent behavior.
  • Ingestion points: Data retrieved via notion.databases.query in SKILL.md (e.g., within the getUrgentSprintTasks function).
  • Boundary markers: The provided code snippets do not implement specific delimiters or warnings to ignore instructions embedded in the retrieved data.
  • Capability inventory: The skill includes write capabilities such as notion.pages.create and notion.blocks.children.append which could be used to persist injected content.
  • Sanitization: The examples do not demonstrate explicit sanitization or filtering of the content retrieved from the Notion API before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 03:37 AM