技术分析-缠论

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:31 PM UTC
• Version:
  1.0.0

Overview

This is a coherent stock-analysis skill, but users should treat the Tushare API token carefully and expect network calls plus local report/chart files.

Install only if you are comfortable giving the skill a Tushare API token and letting it contact market-data services. Prefer setting the token only for the current session or storing it in a restricted secret store instead of appending it to ~/.bashrc. Run it with a dedicated output directory because it creates chart and report files, and treat any trading signals as research rather than investment advice.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The documentation tells users to persist a sensitive API token in ~/.bashrc, which increases the chance of long-lived credential exposure through shell history, accidental file sharing, backups, or overly broad local access. While this is common operational guidance, it lacks any warning about secret handling, least privilege, rotation, or safer alternatives, so it constitutes insecure credential-handling advice.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger phrase at this line is generic enough to match many ordinary stock-analysis requests rather than narrowly invoking this specific ChanLun skill. Because the skill performs file writes and network access without approval, an overly broad trigger can cause unintended activation and execution in contexts where the user did not explicitly request this tool.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: This trigger is ambiguous because it describes a general capability ('趋势判断') that many unrelated market-analysis tools could satisfy. In an agent environment, such ambiguity increases the chance of accidental routing to a skill with network and file-system side effects, which can expose data or produce unintended external calls.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The phrase '买卖点识别' is broad enough to overlap with routine trading-analysis requests and could cause this skill to run when the user did not intend to invoke ChanLun-specific logic. Given the skill's declared network access, file reads, and file writes, mistaken activation has real security and privacy implications beyond simple misclassification.

VirusTotal

66/66 vendors flagged this skill as clean.