inngest-api-cli

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx inngest-cli@latest to download and execute the vendor's command-line interface from the NPM registry. This is an expected operation for interacting with the Inngest service.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands through the Inngest CLI for operations such as debugging runs, syncing applications, and querying insights. It includes warnings against passing sensitive API keys as command-line arguments to avoid exposure in process lists.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Inngest API responses (e.g., function traces, event logs, and SQL query results) and presents this information to the agent for analysis. This creates a potential surface for indirect prompt injection if the API data contains malicious instructions.
  • Ingestion points: API responses fetched by subcommands such as get-function-trace, get-event-runs, and query-insights.
  • Boundary markers: The skill does not define specific delimiters or "ignore" instructions for the agent when processing this external content.
  • Capability inventory: The skill has the ability to execute shell commands and perform network operations via the Inngest CLI.
  • Sanitization: The skill provides guidance to structurally parse JSON output and redact secrets, which mitigates some risks of data exposure but does not fully prevent instruction injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 08:50 PM