Security audit

Crypto One-Way Market

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public crypto candle data and runs a local analysis script, with its network use and optional CSV export disclosed and aligned with its purpose.

Installers should be comfortable with the agent making public Binance-compatible API requests and, if using --output, writing a CSV to the chosen local path. This is market-structure analysis only, not trading advice.

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

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill invokes a Python script that performs network access to Binance and can write files via the documented --output candles.csv option, but the manifest does not declare any tool scope or permissions. This creates a least-privilege gap: an agent or reviewer cannot reliably tell from the manifest that the skill may access external networks and modify local files, increasing the chance of unintended data egress, unsafe execution, or misuse if the script behavior changes.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file instructs reporters to prefer the Chinese phrase "当前 K 线结构更像..." rather than an alternative phrasing, which imposes a specific language choice in the skill's natural-language output. This is a locale/language policy concern because the file does not indicate that Chinese output is optional, user-selected, or justified as region-specific.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The manifest describes pulling OHLCV data and classifying market structure, which is primarily a data retrieval and analysis task. This script additionally persists fetched market data to a user-specified local file via write_csv, a behavior not mentioned in the manifest description.
Content: No source excerpt is available for this finding.