workflow-visualize

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses imperative language ("IMPORTANT: You MUST", "Do NOT skip any step") to enforce strict sequential execution of the workflow tasks.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by design, as it ingests untrusted data into a chain of investigative and generative tools.
  • Ingestion points: The user's prompt is passed as context to the /workflow-start visualize command (SKILL.md).
  • Boundary markers: Absent; user context is interpolated into the workflow without delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill triggers the /scout, /investigate, and /excalidraw-diagram platform tools.
  • Sanitization: No sanitization or validation of the input prompt is performed before it is used to drive the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:25 AM
Security Audit — agent-trust-hub — workflow-visualize