lineage-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs network operations exclusively targeting well-known official services. Specifically,
scripts/get-downstream-reports.pycommunicates with official Microsoft Power BI API endpoints atapi.powerbi.comand authentication endpoints atanalysis.windows.net. These interactions do not involve sensitive local file access or unauthorized data transmission. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of workspace, dataset, and report names retrieved from the Power BI service. This creates a standard surface for indirect prompt injection where malicious metadata could theoretically influence agent behavior, though the script only prints these names to the output.
- Ingestion points: Metadata (workspace names, report names, and dataset names) is ingested from the Power BI API in
scripts/get-downstream-reports.py. - Boundary markers: No explicit delimiters or boundary markers are used when interpolating these strings into the final output.
- Capability inventory: The skill is limited to read-only network requests using the
requestslibrary and does not perform file writes or execute arbitrary commands based on the ingested data. - Sanitization: Input from the API is displayed directly without sanitization, which is typical for reporting and discovery tools.
Audit Metadata