skills/npc-live/clawfirm/square-post/Gen Agent Trust Hub

square-post

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits data to the official Binance API at https://www.binance.com/bapi/composite/v1/public/pgc/openApi/content/add. This interaction is the primary purpose of the skill and targets a well-known service.\n- [PROMPT_INJECTION]: The skill ingests untrusted user content during the content optimization phase, where it is polished for readability before being sent to an external API.\n
  • Ingestion points: User message content (processed in SKILL.md behavior section).\n
  • Boundary markers: None present.\n
  • Capability inventory: Network POST capability via the Binance API.\n
  • Sanitization: No explicit sanitization or validation of the input content is performed before processing.\n- [CREDENTIALS_UNSAFE]: The skill provides instructions for the agent to persist user-provided API keys directly into the SKILL.md file for local state management.\n
  • Evidence: 'Store provided keys: When user provides a new key, update the Accounts section in this file'
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 06:07 AM
Security Audit — agent-trust-hub — square-post