get-to-know-you

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a bash script (scripts/run) that executes a local Node.js module (bin/get-to-know-you.mjs). This is the standard mechanism for this workflow engine to manage the interview state and is not malicious.
  • [PROMPT_INJECTION]: The skill ingests user input through interview questions (Ingestion points: responses to role, stack, and hobby questions). It mitigates the risk of indirect prompt injection by using structured XML boundary markers (e.g., <system>, <prompt>, and <ask-user>) to separate instructions from untrusted data. Its capabilities are restricted to the local execution wrapper and reading skill files (Capability inventory: Bash(scripts/run *), Read).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 05:37 AM
Security Audit — agent-trust-hub — get-to-know-you