notion-core-workflow-a
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external Notion databases, which creates a potential surface for indirect prompt injection attacks if the source data is attacker-controlled.\n
- Ingestion points: Data is ingested via
notion.databases.queryandnotion.databases.retrieveinSKILL.mdandreferences/implementation.md.\n - Boundary markers: The skill documentation and implementation do not define specific delimiters or instructions to ignore potential commands embedded within retrieved database properties.\n
- Capability inventory: The primary capabilities include reading database schemas and querying entries; the skill does not interpolate this data into dangerous tools like shell commands or system evaluations.\n
- Sanitization: No specific content sanitization or filtering is implemented for retrieved text properties like
rich_textortitlefields.
Audit Metadata