retellai-load-scale
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The reference materials include commands requiring elevated privileges for installing testing tools. Evidence:
sudo apt install k6inreferences/load-testing-examples.md.\n- [COMMAND_EXECUTION]: The skill provides instructions for executing shell commands to perform performance testing and manage infrastructure. Evidence:k6 runandkubectl scalecommands inreferences/load-testing-examples.md.\n- [INDIRECT_PROMPT_INJECTION]: The skill implements logic for processing external API responses and system metrics without explicit sanitization, which could be an attack surface for malicious data.\n - Ingestion points: API responses from
api.retellai.comandSystemMetricsdata inreferences/load-testing-examples.md.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded content are used.\n
- Capability inventory: The skill environment has access to
Bash,Write,Edit, andGreptools.\n - Sanitization: The skill does not perform validation or sanitization on the metrics or response content before processing.
Audit Metadata