researching-gourmet-venues
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and processing data from external gourmet review websites and map services.
- Ingestion points: External data is retrieved from services like Tabelog, Google Maps, and OpenRice via web browsing tools.
- Boundary markers: The skill does not explicitly define delimiters for separating external content within the generated files.
- Capability inventory: The skill performs local file writes to a specific
gourmet/directory and utilizes web browsing tools. - Sanitization: While no programmatic sanitization is defined, the workflow requires human-readable audit trails and multi-source verification, which helps mitigate data integrity risks.
- [SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized command execution was found. The use of automation tools like Playwright is limited to the intended purpose of web-based research and is well-documented within the skill's instructions.
Audit Metadata