ClawHub
Back to skill

Security audit

Anki Batch Cards

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a purpose-aligned Anki import helper, but users should understand it can read chosen input files and add persistent notes to Anki.

Install only if you intend to let the agent read the specific TSV/JSON files you provide and add cards to your Anki collection through AnkiConnect. Run any test or dry-run mode first, verify deck and model names, and back up Anki before large imports.

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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation instructs use of local file inputs and network access to AnkiConnect, but does not declare those capabilities. Undeclared file-read and network behavior reduces transparency and can cause an agent or user to authorize actions they did not realize the skill would perform, especially when reading arbitrary local files and sending content to a local service.

Tp4

High
Category
MCP Tool Poisoning
Confidence
84% confidence
Finding
The skill description promises automatic translation and example generation for Spanish-Chinese cards, but the documented behavior mainly passes user-provided TSV/JSON content into Anki fields and does not substantiate those enrichment steps. This mismatch is dangerous because users may trust the skill to perform bounded, purpose-specific processing while it actually supports broader arbitrary field mapping and data injection into Anki.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The skill omits a clear warning that running it will write notes into the user's Anki collection through AnkiConnect. Lack of disclosure can lead to unintended modification of study data, accidental bulk imports, or corruption/duplication when a user believes the operation is only a preview or formatting step.

Static analysis

No suspicious patterns detected.