qbr-builder
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it aggregates content from various external sources to generate reports.
- Ingestion points: Input data is pulled from outreach platforms, CRM systems, delivery trackers, PM notes, and tickets (specified in SKILL.md under 'Inputs').
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the retrieved data.
- Capability inventory: The skill performs file-write operations to markdown files (
<client>-qbr-<YYYY-Qn>.md) and potentially to Notion pages. - Sanitization: There is no evidence of input validation or sanitization for the external data before it is interpolated into the final narrative pages.
Audit Metadata