travel-journal
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 content, such as travel notes and voice memo transcripts, which presents a surface for indirect prompt injection.
- Ingestion points: Raw travel data (notes, transcripts, photo captions) is ingested as the primary input for the skill in the 'What to ask for' section.
- Boundary markers: The instructions do not implement specific delimiters or 'ignore embedded instructions' warnings for the user-provided content.
- Capability inventory: The skill instructs the agent to potentially call external note-saving tools or connectors (specifically mentioning the Scratchpad connector) to store the generated journal entries.
- Sanitization: No explicit sanitization or validation of the user-provided content is performed before it is formatted and saved to external tools.
Audit Metadata