user-profile
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by dynamically learning user preferences from conversation and injecting them into the agent's working instructions.
- Ingestion points: Learns from conversational input and reads from
.agents/user-profile.json(SKILL.md). - Boundary markers: Absent; the skill instructions specify injecting loaded preferences directly into current working instructions.
- Capability inventory: Local file read and write operations targeting
.agents/user-profile.json(SKILL.md). - Sanitization: None; the skill does not define methods to sanitize or validate learned preferences before they are applied to the agent's instruction set.
Audit Metadata