bea-journal
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data provided by the user in the form of legal message exports.
- Ingestion points: The workflow involves processing beA message journals, ZIP archives, and document attachments (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined to separate user-provided document content from the agent's core instructions, nor warnings to ignore embedded instructions in the data.
- Capability inventory: The agent is instructed to unpack ZIP archives, read message metadata (sender, subjects, Safe-ID), and summarize action items based on the content.
- Sanitization: The instructions do not specify any validation, filtering, or sanitization of the content extracted from the external messages before processing.
Audit Metadata