bring-shopping

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'bring-shopping' npm package, which is an unofficial third-party library used to interact with the Bring! API.\n- [COMMAND_EXECUTION]: The skill executes a local Node.js CLI script ('scripts/bring_cli.mjs') to perform list operations, which involves shell execution by the agent.\n- [PROMPT_INJECTION]: The skill ingests external data from the Bring! API (list names and items), creating a potential surface for indirect prompt injection.\n
  • Ingestion points: External data is fetched using 'bring.loadLists()' and 'bring.getItems()' in 'scripts/bring_cli.mjs'.\n
  • Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are used when processing the retrieved list content.\n
  • Capability inventory: The skill has the ability to execute shell commands and access environment variables.\n
  • Sanitization: There is no evidence of sanitization or validation of the content retrieved from the external API before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 12:25 AM