fin-guru-checklist
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The workflow requires the agent to load and apply checklist items to target deliverables, creating an ingestion point for untrusted content. Ingestion points: files within
{project-root}/fin-guru/checklists/and the target deliverables themselves. Boundary markers: The instructions lack explicit delimiters to separate checklist logic from deliverable content. Capability inventory: The skill does not include any tools or executable scripts, minimizing the risk of a successful injection leading to dangerous actions. Sanitization: No input filtering or validation is specified for the deliverables being reviewed. - [NO_CODE]: The skill is comprised solely of markdown instructions and metadata, with no associated Python scripts, Node.js code, or shell commands.
Audit Metadata