pionex-bot

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @pionex/pionex-ai-kit package from the npm registry. This is a vendor-provided resource used to facilitate the intended trading bot management functionality.
  • [COMMAND_EXECUTION]: The skill uses the pionex-trade-cli binary to perform various read and write operations on the Pionex platform, including creating, adjusting, and canceling trading bots. These commands are necessary for the skill's primary purpose and are governed by safety rules requiring explicit user confirmation for write intents.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it ingests data from external sources.
  • Ingestion points: Data is retrieved via order_list, futures_grid get, spot_grid get, smart_copy get, and user_signal_get (documented in SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded in signal descriptions or order metadata.
  • Capability inventory: The skill possesses significant capabilities including file system access (via the CLI tool) and the ability to execute financial transactions (create/cancel bots).
  • Sanitization: No sanitization or validation of the retrieved content is mentioned in the instructions. The primary mitigation is the procedural requirement for human confirmation before executing write operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:37 PM
Security Audit — agent-trust-hub — pionex-bot