notion-research-documentation
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by design, as its core function involves ingesting and processing content from external Notion sources.
- Ingestion points: The
Notion:notion-fetchtool is utilized to retrieve full content from Notion pages (as seen inSKILL.mdandexamples/technical-investigation.md). - Boundary markers: The instructions for synthesis and report generation do not specify the use of delimiters (like XML tags or triple quotes) or system instructions to ignore potential commands embedded in the documents being researched.
- Capability inventory: The skill possesses significant capabilities within the Notion environment, including searching for data (
Notion:notion-search), reading pages (Notion:notion-fetch), and writing/updating documentation (Notion:notion-create-pages,Notion:notion-update-page). - Sanitization: There are no established filters or validation steps to clean the retrieved Notion content before it is passed to the LLM for synthesis, creating a surface for potential instruction override.
Audit Metadata