learn-profile

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by collecting user-provided text (e.g., goals, voice preferences) and saving it to .alvar/LEARNER.md. This file is explicitly designed to be read by other teaching skills to influence future agent behavior. If a user provides malicious instructions during the interview, those instructions will be stored and potentially executed by the agent in later sessions.\n
  • Ingestion points: User responses during the multi-turn interview process (SKILL.md).\n
  • Boundary markers: None. The skill does not instruct the agent to wrap the user-provided data in delimiters or include 'ignore embedded instructions' warnings in the generated file.\n
  • Capability inventory: The skill has the capability to write to the file system to create and update .alvar/LEARNER.md.\n
  • Sanitization: No sanitization, escaping, or validation of user-provided content is performed before writing it to the preference file.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 12:50 PM
Security Audit — agent-trust-hub — learn-profile