Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed crypto market-data helper that calls an external Fía Signals API, with some payment and activation-scope documentation gaps users should notice.
Install only if you are comfortable sending crypto symbols and requested market-data actions to x402.fiasignals.com. Treat non-preview endpoints as potentially paid despite SKILL.md's free-preview table, and avoid letting an agent invoke paid market-data calls without an explicit spending gate.
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
preview|info)
echo "=== Fía Signals — Free Preview ==="
curl -s "${API_BASE}/preview" | python3 -c "
import json, sys
d = json.load(sys.stdin)
r = d.get('preview', {}).get('regime', {})
The README shows commands for invoking paid x402 endpoints and lists prices, but it does not clearly warn that running those commands may trigger a real payment flow or on-chain transaction authorization. In an agent-skill context, users or autonomous agents may execute example commands directly, so insufficient disclosure can lead to unintended spending and unsafe automation behavior.
The skill advertises shell and network-capable behavior but does not declare any explicit tool scope such as permissions or allowed-tools. This creates an authorization ambiguity where an agent may invoke the skill with broader capabilities than users expect, increasing the chance of unintended command execution or external data access.
The trigger description is very broad and overlaps with common market-analysis requests, which can cause the skill to auto-match in many normal conversations. Over-broad activation increases the risk of unnecessary external calls and unintended use of a third-party skill in contexts where the user did not explicitly request it.
The markdown describes real-time market intelligence but does not clearly warn that fulfilling requests sends data to an external third-party API. This is a transparency and privacy issue because users may not realize their prompts or requested symbols are being shared outside the local environment.
No suspicious patterns detected.