Security audit

Auto Report Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its report-generation purpose, but it needs Review because it under-discloses external data and credential handling.

Install only after reviewing or removing the geo-api.yk-global.com verification path. Do not run it with sensitive credentials in OPENAI_API_KEY unless you understand that validation behavior. Use --no-ai or avoid API keys for confidential spreadsheets, and do not run the rm -rf cleanup commands from SKILLHUB.md in a normal environment.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (6)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly advertises AI-driven analysis via an OpenAI-compatible interface for uploaded CSV/Excel data, but the documentation does not warn users that their report contents may be sent to an external provider. This creates a real privacy and data-governance risk because users may upload financial, sales, or other sensitive business data under the assumption processing is local.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill explicitly states that AI analysis uses external providers, but the privacy note says data is processed locally and only AI requests are sent externally without clearly warning that uploaded file contents or extracted data may be included in those requests. This can mislead users about confidentiality and creates a real privacy and compliance risk for sensitive spreadsheets.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The document instructs users to run multiple `rm -rf` commands on absolute paths, but does not prominently warn that deletion is irreversible or advise validating the target path first. In packaging or CI contexts, path confusion, variable substitution mistakes, or copy-paste errors can cause accidental data loss beyond the intended empty directories.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The code sends a prompt derived from the provided DataFrame summary to an external LLM endpoint, but there is no consent, disclosure, redaction, or policy gate before transmission. If the DataFrame contains sensitive, proprietary, or regulated data, this can cause unintended data exfiltration to a third-party service.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The script reads OPENAI_API_KEY from the environment and sends it as a Bearer token to https://geo-api.yk-global.com/validate without clear user consent or a prominent warning. If users store a real OpenAI credential there, this leaks a sensitive secret to an unrelated third party, enabling credential misuse or unauthorized billing.

Missing User Warnings

Low

Confidence: 84% confidence
Finding: The code caches token verification results under the user's home directory without explicit disclosure or any permission hardening. While it does not appear to store the raw token, it still persists account-related metadata such as validity, tier, prefix, plan_id, and quota information that may be sensitive in multi-user or shared environments.

Static analysis

No suspicious patterns detected.