Back to skill

Security audit

Crypto Market Data

Security checks for vulnerabilities and agentic risk

Overview

The skill is a mostly read-only crypto market data client, but its top-level routing text overclaims support for stock and dividend work that the code does not provide.

Install only if you want a CoinGecko-through-AIsa cryptocurrency data CLI. Do not rely on this skill for stocks, dividends, or traditional finance despite the top-level wording, and keep the AISA_API_KEY out of committed files or shared logs.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (9)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The manifest advertises stock analysis, dividend research, and general financial workflows even though the documented behavior is limited to cryptocurrency market data via CoinGecko. This mismatch can cause an agent to invoke the skill for unsupported tasks, producing misleading financial outputs or causing unsafe decision-making based on irrelevant data sources.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README describes the skill as querying cryptocurrency market data via CoinGecko, listing crypto-specific endpoints such as coin details, token prices, trending searches, and crypto news. However, the same line also says to use it for 'stock analysis' and 'dividend research,' which are not supported by the stated crypto-only data source and create a mismatch between claimed use cases and the skill's apparent purpose.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill requires environment access (AISA_API_KEY) and network connectivity to query external AIsa/CoinGecko endpoints, but it does not declare any explicit tool scope such as permissions or allowed-tools. In agent environments that rely on manifest-declared scoping, this can lead to overbroad execution privileges or make security review harder because the actual capabilities are implicit rather than constrained.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest includes overly broad activation triggers for unrelated financial tasks, which can cause this skill to be selected outside its intended crypto-only scope. While this does not by itself execute harmful actions, it expands the opportunity for confusion, bad routing, and inaccurate outputs in automated agent workflows.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest positions the skill as a cryptocurrency market-data tool but also advertises stock analysis and dividend research use cases. This semantic deception increases the chance that orchestration logic or users will route unrelated finance tasks to a crypto-only data source, resulting in incorrect outputs and trust erosion.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The top-level description says the skill is suitable for stock analysis and dividend research, while a later section explicitly says not to use it for equities or traditional finance data. Contradictory instructions are dangerous in agent settings because routing often depends on top-level metadata, so the earlier broad claim may override the more accurate limitation and trigger misuse.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/coingecko_client.py (reported line 55)May include surrounding context.

python
class CoinGeckoClient:
    """AIsa CoinGecko - Unified Cryptocurrency Data API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file implements a CoinGecko client exclusively for cryptocurrency data: coins, token contracts, exchanges, trending, and crypto news. Nothing in the code supports equities, stock analysis, or dividend research, so that part of the manifest's stated use context overclaims the skill's actual behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

For markdown files, warnings should be present when a skill may affect privacy or system integrity. The instruction to set required environment variables implies the skill may use credentials or other sensitive configuration, but the README provides no user-facing caution about handling secrets safely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.