ei-api
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous recipes and workflows for executing shell commands, utilizing both standard utilities like
curlfor API interactions and vendor-specific tools such asedge-impulse-daemonandedge-impulse-uploaderto manage project data and devices.\n- [EXTERNAL_DOWNLOADS]: The agent is instructed to fetch the Edge Impulse OpenAPI specification fromhttps://studio.edgeimpulse.com/openapi.ymlto ensure accurate API usage. It also provides installation instructions for official vendor packages from the npm registry.\n- [PRIVILEGE_ESCALATION]: Setup instructions for the Linux CLI environment include the use ofsudo apt installto obtain necessary system build dependencies and libraries required for the platform's model runners.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, including platform API responses and asynchronous job logs via/jobs/{jobId}/stdout/download, creating a potential surface for instructions embedded in external content to influence the agent's logic.
Audit Metadata