angular-di
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates patterns for services that ingest untrusted data from external sources, establishing a surface for indirect prompt injection.\n
- Ingestion points: SKILL.md (lines 40, 169) and references/di-patterns.md (lines 79, 137, 230, 246) show examples of fetching data via HttpClient and fetch, and reading from localStorage and ActivatedRoute.\n
- Boundary markers: Absent; the code snippets do not include delimiters or instructions to ignore embedded content within the ingested data.\n
- Capability inventory: SKILL.md (lines 20-44) and references/di-patterns.md (lines 60-108) utilize HttpClient for network operations and access browser globals via injection tokens.\n
- Sanitization: Absent; the architectural examples focus on Dependency Injection structure and do not include data validation or escaping logic.
Audit Metadata