flow-qa-report-builder
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's operation is confined to reading local session data (JSON) and individual task reports (Markdown) to generate a consolidated summary. It does not perform network operations, access sensitive system files, or execute shell commands.
- [SAFE]: Although the skill processes external data provided in the QA reports, its capabilities are limited to formatting text and writing files to a specific evidence directory (
qa-evidence/), presenting a negligible attack surface for indirect prompt injection. - [SAFE]: The reliance on an external PDF conversion skill ([PDF_SKILL]) is a standard pattern for modular agent workflows and does not introduce security vulnerabilities within this skill's implementation.
Audit Metadata