bitrix
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto interact with the Bitrix24 API andjqto parse JSON responses. It also demonstrates writing temporary JSON files to/tmp/bitrix_request.jsonfor POST request bodies. - [EXTERNAL_DOWNLOADS]: Performs network requests to
bitrix24.comto manage CRM data (leads, deals, contacts) and tasks. Bitrix24 is a well-known CRM service. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection if data retrieved from the Bitrix24 API contains malicious instructions.
- Ingestion points: API response data from leads, contacts, and tasks (e.g.,
SKILL.mdexamples for listing leads and tasks). - Boundary markers: None present in the provided shell examples.
- Capability inventory: Shell command execution via
curlandjq, file system access (writing to/tmp/). - Sanitization: No explicit sanitization of the API data is performed before it is processed by the agent.
Audit Metadata