reports-analytics
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data to generate structured artifacts like CSV, SQL, and JSON Schema templates.\n
- Ingestion points: Step 2 captures user-supplied descriptions regarding 'Current process', 'Content', and 'Data'.\n
- Boundary markers: The skill instructions do not define specific delimiters (e.g., XML tags or triple quotes) or 'ignore embedded instructions' warnings for the data being ingested and processed.\n
- Capability inventory: The skill can perform file-writing operations for artifact generation and delegates tasks to the
@notion-manual-importagent/tool.\n - Sanitization: There are no instructions to sanitize, escape, or validate the user-provided descriptions before they are interpolated into the generated SQL DDL or other template outputs.
Audit Metadata