notion
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external Notion pages.
- Ingestion points: Data is retrieved via
getContentCalendar()andgetNotionPage(pageId)as described inSKILL.md. - Boundary markers: The documentation does not specify the use of delimiters or clear instructions to the agent to treat Notion content as untrusted data.
- Capability inventory: The documented actions (
content-calendar,notion-page) are read-only; no dangerous capabilities like shell execution or file writes are exposed. - Sanitization: There is no evidence of content filtering or sanitization before the data is presented to the agent.
Audit Metadata