research-documentation
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill automates gathering information from the web and processing it into a Notion database, creating a vulnerability where malicious instructions embedded in external web pages could influence the agent's behavior or poison the documentation.
- Ingestion points: The skill uses web access to gather information from external online sources as specified in the workflow in SKILL.md.
- Boundary markers: There are no documented boundary markers or instructions to ignore potentially malicious content within the gathered research data.
- Capability inventory: The skill possesses the capability to create and update content in a Notion database via the Notion API, as well as generate summary reports (SKILL.md).
- Sanitization: There is no evidence of content sanitization or validation of the data retrieved from external web sources before it is processed and stored in Notion.
Audit Metadata