family-history-notes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided data (genealogical records, transcriptions, and abstracts) and maintains the capability to write this data to external note-taking tools.
- Ingestion points: Untrusted data enters the agent context through the "records" provided by the user, which include transcriptions, abstracts, or descriptions of genealogical findings as defined in the "What to ask for" section of
SKILL.md. - Boundary markers: Absent. The instructions do not define delimiters or provide warnings for the agent to ignore instructions that may be embedded within the historical record text.
- Capability inventory: The skill possesses the capability to interact with external tools, specifically the "Scratchpad connector" or other connected notes tools, to create or update notes based on the processed data.
- Sanitization: Absent. There are no instructions for the agent to sanitize, escape, or validate the content of the records before incorporating them into the final output or sending them to the notes tool.
Audit Metadata