chat-format
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and tool usage are consistent with its stated purpose of prompt formatting and context retrieval using vendor-specific tools (ruvllm_*) provided by the author (ruvnet).
- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by retrieving context from indexed documents and injecting it into chat prompts for external providers.
- Ingestion points: Document addition via mcp__claude-flow__ruvllm_hnsw_add in SKILL.md.
- Boundary markers: None explicitly mentioned in the skill instructions to delimit retrieved context.
- Capability inventory: Formatting chat messages for LLM providers via mcp__claude-flow__ruvllm_chat_format.
- Sanitization: No sanitization or validation of indexed document content is described.
Audit Metadata