notion-research-documentation
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core workflow involves fetching and synthesizing content from external, potentially untrusted sources, which creates a vulnerability surface for indirect prompt injection.\n
- Ingestion points: The skill utilizes
Notion:notion-fetchinSKILL.mdto retrieve full page content and search results. Additionally,reference/advanced-search.mdindicates the agent may process data from connected third-party integrations such as Slack, Google Drive, GitHub, and Jira.\n - Boundary markers: The instructions in
SKILL.mdand the templates inreference/do not provide the agent with specific delimiters or "ignore embedded instructions" warnings to separate research data from the system prompt.\n - Capability inventory: The agent has the capability to write synthesized information back to the workspace using
Notion:notion-create-pages(noted inSKILL.md), which could be abused if malicious instructions are present in the fetched documents.\n - Sanitization: There are no requirements or guidelines provided within the skill's reference files or workflow steps for sanitizing, escaping, or validating content retrieved from external sources before interpolation into research documents.
Audit Metadata