lightfast-inngest

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
  • Ingestion points: Untrusted user data is ingested via the $ARGUMENTS variable in command/lightfast-inngest.md.
  • Boundary markers: The skill uses <user-request> tags to delimit the input, which provides basic structural separation but does not prevent malicious instruction execution.
  • Capability inventory: The skill has access to MCP tools for listing, invoking, and sending events to a local server.
  • Sanitization: No input validation or sanitization of the arguments is documented in the skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 10:50 AM
Security Audit — agent-trust-hub — lightfast-inngest