premium-hotels
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides shell command templates for querying local JSON files using jq and bash. These templates include shell variable assignments (e.g., LAT, LNG, R) that are intended to be populated based on user input. This pattern introduces a potential command injection surface if the agent does not properly sanitize user-provided values before passing them to the shell.- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from local JSON files to generate recommendations and comparison tables. This creates a surface for indirect prompt injection if the source data contains malicious instructions.
- Ingestion points: data/fhr-properties.json, data/thc-properties.json, and data/chase-edit-properties.json.
- Boundary markers: No delimiters or explicit warnings to ignore embedded instructions are present.
- Capability inventory: The skill utilizes shell command execution via jq to process and output data.
- Sanitization: No explicit sanitization or validation of the JSON content is performed before interpolation into the prompt.- [EXTERNAL_DOWNLOADS]: The documentation references external URLs for refreshing hotel data from Google My Maps. These links target a well-known service and are provided for informational purposes without automated download or execution logic.
Audit Metadata