workflow-big-feature
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests user prompts to trigger a complex workflow, creating a surface for indirect prompt injection where malicious data could influence downstream agent actions. Ingestion points: User prompt passed as context to the /workflow-start command in SKILL.md. Boundary markers: Absent; the skill does not define separators to isolate user input from its own instructions. Capability inventory: The workflow involves tools for web research and code generation (via /cook) as listed in the command sequence. Sanitization: No validation or sanitization of the input data is described in the skill configuration.
Audit Metadata