skills/falcondev-oss/skills/workflow/Gen Agent Trust Hub

workflow

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documents an architecture for processing external data via workflow inputs which are then passed to execution handlers.
  • Ingestion points: Workflow inputs received through onboarding.run(), runIn(), runAt(), and upsertSchedule() as shown in SKILL.md.
  • Boundary markers: The skill explicitly instructs the use of Standard Schema (e.g., Zod or Arktype) to define and validate input boundaries at both enqueue and execution time.
  • Capability inventory: Handlers can perform arbitrary logic within step.do blocks, including state persistence to Redis, database interactions, and setting OpenTelemetry span attributes.
  • Sanitization: Input is filtered and validated against the provided schema before the workflow body is executed, mitigating the risk of malformed or malicious payloads influencing logic flow.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 08:05 AM