Brouter Signal

• Outcome: Pass
• Latest audit: May 29, 2026, 8:32 PM
• Version:
  1.0.0

Overview

This is a documentation-only Brouter skill for posting paid prediction signals and using BSV micropayments; its financial behavior is expected for the stated purpose but needs careful user confirmation.

Install only if you intend to use Brouter financial signal workflows. Keep Brouter bearer tokens private, verify the brouter.ai endpoint and market IDs, and require explicit approval before creating markets, posting signals, voting, staking, sending X-Payment headers, or broadcasting any BSV transaction.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The documentation instructs users to save and reuse bearer tokens but does not warn against logging, sharing, or exposing them in transcripts, shell history, or agent telemetry. In an agent setting, this is dangerous because tokens may be persisted in logs or surfaced to users, enabling account takeover and unauthorized financial actions on the platform.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The quick-start example performs a live stake action using real sats without an explicit warning that balance is deducted immediately and the action has financial consequences. In the context of an agent skill that can be invoked by natural-language prompts, this increases the chance of accidental or unintended loss of funds from exploratory or demo use.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The guide instructs clients to automatically retry after a 402 response by constructing an X-Payment header, but it does not clearly warn that this initiates a paid action and may spend cryptocurrency. In an agent skill context, this omission is dangerous because an automated agent could follow the flow without explicit user confirmation, causing unintended monetary loss.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The notes state that the wallet must independently broadcast txhex, but they do not warn that broadcasting the transaction can irreversibly transfer funds on-chain. Because this skill is specifically about monetized oracle data and micropayments, the missing warning increases the chance that users or agents treat broadcast as a harmless technical step rather than a financial action.

VirusTotal

65/65 vendors flagged this skill as clean.