scenario-workflows
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to process external user data as inputs for workflow execution, creating a potential surface for indirect prompt injection. 1. Ingestion points: The inputs object for the workflow_run tool derived from user requests (SKILL.md). 2. Boundary markers: The instructions lack explicit delimitation or warnings to ignore embedded commands within processed data. 3. Capability inventory: The skill utilizes tools for workflow execution (workflow_run), status monitoring (jobs_wait), and asset display (asset_display). 4. Sanitization: No specific sanitization or validation logic for user-provided inputs is described in the skill documentation.
Audit Metadata