Security audit

Free Novel Search

Security checks across malware telemetry and agentic risk

Overview

This skill is a novel-search helper, but it needs review because it presents legally uncertain sources and weak license checks as more trustworthy than the artifacts support.

Install only if you are comfortable manually verifying each recommended platform and work. Do not treat the license checker as proof of legality, avoid sensitive search queries, and treat results from the network search as advisory because HTTPS verification is disabled.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Intent-Code Divergence

Medium

Confidence: 92% confidence
Finding: The skill explicitly claims to guide users toward legitimate free novel sources, but the curated list includes several sites commonly associated with unauthorized or legally ambiguous distribution without caveats or verification guidance attached to those entries. This creates a trust mismatch: users may rely on the skill's framing and be steered toward infringing sources, exposing them to legal, reputational, and potentially malware-related risks from low-trust sites.

Intent-Code Divergence

Medium

Confidence: 97% confidence
Finding: The CLI exposes a `--verify-license` option and describes it as performing license determination, but the flag is never used. This creates a deceptive security signal: users may believe the tool performed a substantive license check when it only applies URL heuristics, leading to unsafe reliance on incorrect results.

Intent-Code Divergence

Medium

Confidence: 95% confidence
Finding: The module docstring and CLI descriptions claim the script can determine whether content is 'truly free and legal,' but the implementation only checks the input URL string against hard-coded domains and regexes. In a security-sensitive context, this overclaim can mislead users into trusting a legal/compliance assessment that was never actually performed.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The script sends user-provided search terms to external services (Gutendex and Open Library) without any explicit warning or consent mechanism, which can expose sensitive queries to third parties. This is more concerning in an agent skill context because users may assume local processing while the skill transmits potentially private reading interests or other sensitive text off-system.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.insecure_tls_verification

HTTPS certificate verification is disabled.

Warn

Code: suspicious.insecure_tls_verification
Location: scripts/search_novels.py:77