notion-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes content and comments from Notion, which may contain malicious instructions designed to influence the agent's logic.
- Ingestion points: Data is ingested via
notion.blocks.children.listandnotion.comments.listas seen inreferences/implementation.md(Steps 1 and 6). - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore or treat content retrieved from Notion as untrusted data.
- Capability inventory: The skill is configured with
WriteandBashtool access in theSKILL.mdfrontmatter and includes logic for modifying or deleting blocks and comments in Notion. - Sanitization: The
blockToTextutility inreferences/implementation.mdflattens Notion rich text into plain strings without implementing validation, escaping, or filtering of the processed content.
Audit Metadata