chat-format
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill defines an ingestion point for external data through the HNSW routing tool within SKILL.md. There are no explicit boundary markers or sanitization steps specified for the retrieved document context. The agent's capability inventory includes the Bash tool and prompt formatting utilities. While this presents a surface area for indirect prompt injection from processed documents, the skill's own logic does not contain malicious instructions or safety bypasses.
- [SAFE]: A comprehensive analysis found no evidence of obfuscation, hardcoded credentials, or unauthorized remote code execution. The toolset and execution flow are consistent with the skill's stated purpose of prompt formatting and context retrieval.
Audit Metadata