report-editor
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill downloads and inspects existing report files (RDLX-JSON and manifest) using the dxs CLI. This introduces a surface for indirect prompt injection where instructions embedded in the report content or expressions could be interpreted by the agent during the Download and Inspect phase.
- Ingestion points: Phase 1: Download & Inspect (SKILL.md)
- Boundary markers: Absent
- Capability inventory: File system access, modification, and network upload via dxs CLI (SKILL.md)
- Sanitization: Absent
Audit Metadata