cn-prd-review
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed exclusively of markdown instructions and templates for the agent to follow. It does not include any scripts, binary files, or configuration parameters that execute code on the host system.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external Product Requirements Documents (PRDs) provided by users. This represents an attack surface for indirect prompt injection if a PRD contains hidden instructions. However, because the skill does not have access to any tools (such as network, filesystem, or shell execution), the potential impact of such an injection is effectively mitigated.
- Ingestion points: Processes user-provided PRD content and meeting summaries.
- Boundary markers: No specific delimiters are used to wrap untrusted input.
- Capability inventory: No tools or capabilities are requested or used.
- Sanitization: No input validation or sanitization is implemented.
Audit Metadata