workflow-e2e-from-recording
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs high-pressure imperative language ("IMPORTANT", "MUST", "Do NOT skip") intended to override the agent's internal task prioritization and force strict adherence to a specific command sequence.
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting untrusted user input as the primary context for a multi-step workflow without established boundary markers or sanitization.
- Ingestion points: User prompt is passed as context to the
/workflow-startcommand inSKILL.md. - Boundary markers: Absent. The skill does not define delimiters or instructions to ignore embedded commands within the user input.
- Capability inventory: The workflow includes steps such as
/e2e-testand/test, which involve generating and executing Playwright test code, implying file system and shell access. - Sanitization: Absent. There is no evidence of validation or escaping for the user-provided context.
Audit Metadata