workflow-test-verify
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill is composed of markdown instructions and does not contain any executable scripts, binaries, or external code.
- [PROMPT_INJECTION]: The instructions utilize directive language such as 'IMPORTANT' and 'MUST' to ensure the agent follows the workflow sequence. These are categorized as functional requirements rather than attempts to bypass safety filters.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by using the user's prompt as context for the tools invoked in the workflow. Ingestion points: User prompt provided during skill activation (SKILL.md). Boundary markers: Absent; user input is passed directly as context. Capability inventory: The workflow calls several tools including '/scout', '/integration-test', and '/test', which likely interact with the environment (SKILL.md). Sanitization: No validation or escaping is performed on the user context.
Audit Metadata