memory-contract

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): This skill is susceptible to indirect prompt injection because it ingest and summarizes external user data through the flowbabyRetrieveMemory and flowbabyStoreSummary tools.
  • Ingestion points: SKILL.md describes tools flowbabyRetrieveMemory and flowbabyStoreSummary which pull data from prior sessions and user interactions.
  • Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore instructions found within retrieved memory.
  • Capability inventory: The skill is designed to guide reasoning and influence future tool calls based on retrieved data.
  • Sanitization: Absent. There is no evidence of input validation or sanitization for the data retrieved from memory.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:46 PM