workflow-investigation

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface where user-provided context is passed directly to investigation tools. 1. Ingestion points: User prompt context passed to '/workflow-start investigation' in SKILL.md. 2. Boundary markers: No delimiters or instructions to disregard embedded commands are present. 3. Capability inventory: The workflow executes '/scout' and '/investigate', which involve file system exploration. 4. Sanitization: No input validation or sanitization is implemented for the ingested context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 03:50 AM