Security audit

小果通达信公式转Python

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed technical-analysis and formula-conversion reference, with local file output risks users should control but no evidence of hidden or malicious behavior.

Install only if you want a broad Tongdaxin-to-Python quant-analysis reference. When using its conversion helper, choose explicit input and output paths, keep outputs in a working directory, review generated Python before running it, and treat trading signals as analysis rather than automatic trading advice.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (2)

Context-Inappropriate Capability

Medium

Confidence: 95% confidence
Finding: The skill includes a formula-conversion helper that reads an arbitrary local file and writes generated Python code to an output path. Even though this is framed as a convenience feature, it expands the skill from pure indicator computation into local file I/O and code generation, which can overwrite files, process unintended inputs, or facilitate unsafe later execution of generated code.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger list is extremely broad and contains many generic finance terms, increasing the chance that the skill is invoked in contexts where the user did not intend to activate it. In an agent environment, overbroad activation can cause unintended tool use, exposing users to misleading outputs, risky code paths, or unnecessary access to local/external resources referenced by the skill.

Static analysis

No suspicious patterns detected.