notion-knowledge-capture
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it extracts and structures information from untrusted conversation contexts. Malicious instructions placed in the chat could be processed by the agent and executed via the Notion tools. \n
- Ingestion points: Conversation context is the primary data source as defined in
SKILL.mdand shown inexamples/.\n - Boundary markers: There are no instructions to use delimiters or ignore embedded commands within the extracted data.\n
- Capability inventory: The skill uses
Notion:notion-search,Notion:notion-create-pages, andNotion:notion-update-page, allowing for data access and modification.\n - Sanitization: No mention of validation or filtering for the processed conversation content.
Audit Metadata