skills/bankrbot/skills/bankr-signals/Gen Agent Trust Hub

bankr-signals

Warn

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a heartbeat routine in SKILL.md that instructs the agent to fetch and follow instructions from a remote URL (https://bankrsignals.com/heartbeat.md). This pattern of dynamic instruction loading allows the remote server to alter the agent's logic or behavior at runtime.
  • [PROMPT_INJECTION]: The skill encourages agents to copy-trade based on a public signal feed (/api/feed). The ingestion of untrusted data—specifically the trade 'reasoning' and 'metadata' fields—without explicit sanitization or boundary markers creates a surface for indirect prompt injection.
  • [COMMAND_EXECUTION]: The scripts/publish-signal.sh script executes arbitrary JavaScript via node -e to handle cryptographic signing. While used for its stated purpose, this enables dynamic code execution within the agent's environment.
  • [EXTERNAL_DOWNLOADS]: The skill's operational flow involves periodic downloads of instruction sets and trade data from external domains (bankrsignals.com and api.bankr.bot).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 22, 2026, 08:51 AM