rapport-builder
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown instructions, guiding principles, and communication frameworks. There are no scripts, binaries, or automated tasks associated with this skill.
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, obfuscation, or privilege escalation were detected. The skill focuses on providing the agent with soft-skills guidance based on established negotiation and psychology literature.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided conversational data to offer communication advice, it lacks any executable capabilities (file writing, network calls, or system commands) that could be exploited via malicious data ingestion. The attack surface is minimal and limited to the quality of advice generated.
Audit Metadata