analyzing-change-for-testing
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external project artifacts such as requirements (PRDs), design documents, and source code changes. This creates a surface for indirect prompt injection if those artifacts contain malicious instructions.
- Ingestion Points: The skill reads
artifact-routing.md, "current change basis", and "related project materials". - Boundary Markers: The skill relies on structured Markdown templates (
test-analysis-template.md) to segregate analysis findings, though it does not explicitly define escape sequences for untrusted data. - Capability Inventory: Capabilities are limited to generating reports and calling other analysis-focused skills. The instructions explicitly forbid the agent from creating development tickets, branches, or commits, which significantly mitigates the risk of an injection translating into harmful actions.
- Sanitization: No explicit sanitization of external data is mentioned, but the output is restricted to analysis summaries and templates.
Audit Metadata