Security audit

Currency Forecast

Security checks for vulnerabilities and agentic risk

Overview

This currency-analysis skill is purpose-aligned and does not show hidden, destructive, persistent, or credential-seeking behavior, though its claimed forecasting capability is overstated by the included stub script.

Install only if you are comfortable with currency-analysis requests potentially using external API and web-search services. Treat outputs cautiously because the included script does not currently perform real exchange-rate analysis or forecasting.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill exposes broad natural-language invocation examples like 'Analyze AUD/CNY exchange rate' and 'Check if AUD/CNY is below 4.82' without defining tighter activation boundaries or requiring explicit user confirmation before tool use. In agent ecosystems, this can cause over-triggering or accidental activation from conversational text, which may lead to unintended external API calls or web searches.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill states it uses Frankfurter API and web_search but does not warn users that their prompts, currency pairs, thresholds, or related context may be transmitted to third-party services. This creates a privacy and data-handling risk because users may unknowingly provide sensitive business, trading, or proprietary financial intent information that is sent externally.

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: The manifest describes a tool that provides technical analysis, market research, and predictive insights for currency pairs. In contrast, `analyze_currency` returns a static skeleton response with all analytical fields set to `None`, so the implemented behavior does not match the claimed capability.

Intent-Code Divergence

Low

Confidence: 88% confidence
Finding: The comments suggest expected operational behavior—fetching exchange-rate data from an API—but the code immediately returns a stub object without any fetch or computation. This is an intent-code divergence because the documentation implies a behavior the implementation does not perform.

Static analysis

No suspicious patterns detected.