ClawHub
Back to skill

Security audit

market-briefing-assistant

Security checks for vulnerabilities and agentic risk

Overview

This market-data skill is a clearly scoped helper that queries named AirnodeHub providers and includes approval checks for paid or credentialed calls.

Before installing, be aware that this skill can direct an agent to send market-data requests to AirnodeHub provider endpoints and may involve paid, credentialed, or subscription calls, though the instructions require explicit approval before those calls. It does not contain executable code or persistence.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Scope Creep

Low
Category
Excessive Agency
Content
3. Choose specialist operations: TickerLayer `snapshot` or Twelve Data `quote` for current prices; Benzinga `news` for narrow company news; Benzinga `earnings`/`earningReports` or Twelve Data `earnings` for earnings; Twelve Data `statistics` or detailed statement operations for fundamentals; and Twelve Data specialist indicator operations for RSI, MACD, ATR, Bollinger Bands, or stochastic oscillator. Keep histories and output sizes small. **Done when:** each requested category has a minimal call plan.

4. Before any paid, credentialed, subscription, or uncertain-cost POST, state the calls and cost and obtain explicit approval. Combine compatible requests and never silently expand scope. **Done when:** calls are free, approved, or blocked before cost.

5. POST `{"operation":"<operation>","parameters":{...}}` to each selected listing. Validate symbol, exchange, dates, interval, units, freshness, and whether values are live, completed bars, filed facts, estimates, or computed indicators. Prefer a second authorized specialist source for consequential price claims. **Done when:** attested data or exact blockers are available.
Confidence
75% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.