financial-planning-workflow
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates a workflow where the agent ingests and analyzes external, untrusted client data, creating an indirect prompt injection surface. * Ingestion points: Data gathering phase described in
SKILL.md(e.g., tax returns, statements). * Boundary markers: Instructions lack delimiters or guidance to ignore instructions embedded in data. * Capability inventory: Access toBash,Read,Write, andEdittools. * Sanitization: No validation or filtering of external input is prescribed. - [NO_CODE]: The skill consists exclusively of instructional Markdown and does not include any accompanying scripts or executable files.
Audit Metadata