user-profile-interview

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted input from the user during the conversational interview and reads data from local system files without explicit sanitization or boundary markers.
  • Ingestion points: User messages (Phase 1 & 2) and the agent_file_system/USER.md file (read via read_file).
  • Boundary markers: Absent. The instructions do not define delimiters or tags to isolate untrusted user content from agent instructions during processing.
  • Capability inventory: The skill uses stream_edit to modify system configuration files (USER.md and AGENT.md) and send_message to communicate with the user.
  • Sanitization: Absent. The agent is instructed to write user-supplied goals and derived personality observations directly into markdown files as free-form text or paragraphs without validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 01:51 PM
Security Audit — agent-trust-hub — user-profile-interview