access-travel-integration
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a shell script (scripts/fetch-attractions.sh) that retrieves attraction metadata from the vendor's official domain (static.accessdevelopment.com) to synchronize the local reference file references/attractions-and-identifiers.json with the platform's current inventory.\n- [COMMAND_EXECUTION]: Instructions in the main skill body direct the agent to execute the fetch-attractions.sh shell script to ensure that the attraction identifiers used for deep linking are current and accurate.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface where it reads from a local JSON file populated via a remote web request to the vendor's site. While this facilitates looking up identifiers for deep links, it technically allows external content into the agent's context. The risk is assessed as minimal given the structured nature of the name and ID pairs.
Audit Metadata