diagram-reports-generator
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external markdown files which constitutes an attack surface for indirect prompt injection.
- Ingestion points: Chapter markdown files located in the
docs/chapters/directory are parsed by thescripts/diagram-report.pyscript. - Boundary markers: Absent. The parsing logic relies on regex patterns (e.g.,
#### Diagram:) to extract content but lacks explicit delimiters to ignore or neutralize embedded instructions. - Capability inventory: The script performs file writing operations to generate reports in the
docs/learning-graph/directory. - Sanitization: Absent. Extracted text from the chapter files is directly interpolated into the generated markdown and HTML reports without sanitization or escaping.
Audit Metadata