rnd-aspice-requirements-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
- Ingestion points: User-provided requirement documents (SYS.1, SYS.2, or SWE.1) during the information collection phase (SKILL.md).
- Boundary markers: Absent; the skill lacks explicit delimiters or specific instructions to distinguish between the requirements text and potential malicious instructions.
- Capability inventory: The skill generates structured markdown reports, which is the primary output channel for potential injection (SKILL.md, Phase 7).
- Sanitization: No validation, filtering, or content escaping is performed on the ingested document data.
Audit Metadata