lgpd-ropa
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from multiple markdown files in the
.lgpd/directory to generate a consolidated report. This creates a surface where instructions embedded in the source data could potentially influence the agent's behavior during the consolidation process. - Ingestion points:
.lgpd/data-map.md,.lgpd/legal-basis.md,.lgpd/encarregado.md,.lgpd/vendors/,.lgpd/transfers/, and.lgpd/retention.md. - Boundary markers: Absent. The instructions do not specify delimiters or constraints to prevent the agent from following instructions found within the input files.
- Capability inventory: The skill is designed to read multiple local files and write a consolidated document to
.lgpd/ROPA.md. - Sanitization: Absent. There are no mentions of filtering or escaping content read from the source files before consolidation.
Audit Metadata