mapping-project-test-space
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes a wide range of external, potentially untrusted data sources to build its test map.
- Ingestion points: The skill reads
test-privateer/references/artifact-routing.mdand processes PRDs, user/business flow documents, architecture diagrams, source code, and interface/data contracts. - Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore embedded instructions within the ingested data.
- Capability inventory: The skill leverages several analysis tools (
clarifying-test-basis,scanning-product-with-sfdipot,analyzing-test-space-with-mfq,analyzing-product-risks) which might be susceptible to manipulation by malicious content inside the analyzed documents. - Sanitization: There is no mention of sanitization, filtering, or escaping of the external content before it is processed by the agent.
Audit Metadata