zergbnb-skill
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to interact with a local CLI (npm run cli) for platform management. This includes performing searches, managing reservations, and administering payments. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external listing searches and property facts which could contain adversarial instructions targeting the agent's logic.
- Ingestion points: Data retrieved from
listings searchandproperties extract-factsas documented inSKILL.md. - Boundary markers: The instructions do not provide explicit delimiters or "ignore instructions" warnings for the data being processed.
- Capability inventory: The skill has access to the
Bashtool and can perform financial actions (reservations book), administrative changes (admin set-mode), and data modification. - Sanitization: There are no documented procedures for sanitizing or filtering content received from the zergbnb API before processing.
Audit Metadata