workflow-testing

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it passes the user's prompt directly into the workflow context without sanitization or delimiters.\n
  • Ingestion points: User prompt is passed as context to the /workflow-start testing command in SKILL.md.\n
  • Boundary markers: Absent. There are no instructions or delimiters to isolate the user-provided context from the workflow's command structure.\n
  • Capability inventory: The skill triggers internal workflow commands /test and /workflow-end. No high-risk capabilities such as file system modification, network access, or code execution were found in the provided file.\n
  • Sanitization: Absent. The skill does not perform any validation or escaping on the user's input before using it in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 03:50 AM