x-mentor-skill-nuwa

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted input when the user pastes tweets for review or provides account data for diagnostics, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: User-pasted tweet content in Scenario B and pasted account export data in Scenario E.
  • Boundary markers: Absent; there are no instructions to the agent to disregard embedded commands in the processed data.
  • Capability inventory: The skill facilitates file writing to the local user-data/ directory and potentially uses browser tools to collect data.
  • Sanitization: No sanitization or validation of external content is specified before the agent processes or saves the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 12:45 AM